파이썬 distutils가 CUDA 코드를 컴파일 할 수 있습니까?

Question

나는 distutils를 사용하여 파이썬에 동적 라이브러리를 만들고 싶습니다. CUDA 코드가 있습니다. 하지만 distutils는 "nvcc"컴파일러가 설치되어 있어도 ".cu"파일을 인식하지 못합니다. 그것을 완료하는 방법을 모르겠습니다.

Answer 1

Distutils는 다중 컴파일러를 동시에 사용할 수 없기 때문에 기본적으로 CUDA를 컴파일 할 수 없습니다. 기본적으로 플랫폼에 기반한 컴파일러로 설정하고 소스 코드의 유형에는 설정하지 않습니다.

distutils에 원숭이 패치가 들어있는 github 예제 프로젝트에서이를 지원합니다. 예제 프로젝트는 일부 GPU 메모리와 CUDA 커널을 관리하고 swig로 랩핑 한 C++ 클래스이며 모두 python setup.py install으로 컴파일됩니다. 배열 작업에 중점을두고 있으므로 numpy도 사용하고 있습니다. 이 예제 프로젝트에서 커널이 수행하는 모든 작업은 배열의 각 요소를 하나씩 증가시킵니다.

코드는 여기 https://github.com/rmcgibbo/npcuda-example입니다. 다음은 setup.py 스크립트입니다. 전체 코드의 핵심은 customize_compiler_for_nvcc()입니다.

import os 
from os.path import join as pjoin 
from setuptools import setup 
from distutils.extension import Extension 
from distutils.command.build_ext import build_ext 
import subprocess 
import numpy 

def find_in_path(name, path): 
    "Find a file in a search path" 
    #adapted fom http://code.activestate.com/recipes/52224-find-a-file-given-a-search-path/ 
    for dir in path.split(os.pathsep): 
     binpath = pjoin(dir, name) 
     if os.path.exists(binpath): 
      return os.path.abspath(binpath) 
    return None 


def locate_cuda(): 
    """Locate the CUDA environment on the system 

    Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64' 
    and values giving the absolute path to each directory. 

    Starts by looking for the CUDAHOME env variable. If not found, everything 
    is based on finding 'nvcc' in the PATH. 
    """ 

    # first check if the CUDAHOME env variable is in use 
    if 'CUDAHOME' in os.environ: 
     home = os.environ['CUDAHOME'] 
     nvcc = pjoin(home, 'bin', 'nvcc') 
    else: 
     # otherwise, search the PATH for NVCC 
     nvcc = find_in_path('nvcc', os.environ['PATH']) 
     if nvcc is None: 
      raise EnvironmentError('The nvcc binary could not be ' 
       'located in your $PATH. Either add it to your path, or set $CUDAHOME') 
     home = os.path.dirname(os.path.dirname(nvcc)) 

    cudaconfig = {'home':home, 'nvcc':nvcc, 
        'include': pjoin(home, 'include'), 
        'lib64': pjoin(home, 'lib64')} 
    for k, v in cudaconfig.iteritems(): 
     if not os.path.exists(v): 
      raise EnvironmentError('The CUDA %s path could not be located in %s' % (k, v)) 

    return cudaconfig 
CUDA = locate_cuda() 


# Obtain the numpy include directory. This logic works across numpy versions. 
try: 
    numpy_include = numpy.get_include() 
except AttributeError: 
    numpy_include = numpy.get_numpy_include() 


ext = Extension('_gpuadder', 
       sources=['src/swig_wrap.cpp', 'src/manager.cu'], 
       library_dirs=[CUDA['lib64']], 
       libraries=['cudart'], 
       runtime_library_dirs=[CUDA['lib64']], 
       # this syntax is specific to this build system 
       # we're only going to use certain compiler args with nvcc and not with gcc 
       # the implementation of this trick is in customize_compiler() below 
       extra_compile_args={'gcc': [], 
            'nvcc': ['-arch=sm_20', '--ptxas-options=-v', '-c', '--compiler-options', "'-fPIC'"]}, 
       include_dirs = [numpy_include, CUDA['include'], 'src']) 


# check for swig 
if find_in_path('swig', os.environ['PATH']): 
    subprocess.check_call('swig -python -c++ -o src/swig_wrap.cpp src/swig.i', shell=True) 
else: 
    raise EnvironmentError('the swig executable was not found in your PATH') 



def customize_compiler_for_nvcc(self): 
    """inject deep into distutils to customize how the dispatch 
    to gcc/nvcc works. 

    If you subclass UnixCCompiler, it's not trivial to get your subclass 
    injected in, and still have the right customizations (i.e. 
    distutils.sysconfig.customize_compiler) run on it. So instead of going 
    the OO route, I have this. Note, it's kindof like a wierd functional 
    subclassing going on.""" 

    # tell the compiler it can processes .cu 
    self.src_extensions.append('.cu') 

    # save references to the default compiler_so and _comple methods 
    default_compiler_so = self.compiler_so 
    super = self._compile 

    # now redefine the _compile method. This gets executed for each 
    # object but distutils doesn't have the ability to change compilers 
    # based on source extension: we add it. 
    def _compile(obj, src, ext, cc_args, extra_postargs, pp_opts): 
     if os.path.splitext(src)[1] == '.cu': 
      # use the cuda for .cu files 
      self.set_executable('compiler_so', CUDA['nvcc']) 
      # use only a subset of the extra_postargs, which are 1-1 translated 
      # from the extra_compile_args in the Extension class 
      postargs = extra_postargs['nvcc'] 
     else: 
      postargs = extra_postargs['gcc'] 

     super(obj, src, ext, cc_args, postargs, pp_opts) 
     # reset the default compiler_so, which we might have changed for cuda 
     self.compiler_so = default_compiler_so 

    # inject our redefined _compile method into the class 
    self._compile = _compile 


# run the customize_compiler 
class custom_build_ext(build_ext): 
    def build_extensions(self): 
     customize_compiler_for_nvcc(self.compiler) 
     build_ext.build_extensions(self) 

setup(name='gpuadder', 
     # random metadata. there's more you can supploy 
     author='Robert McGibbon', 
     version='0.1', 

     # this is necessary so that the swigged python file gets picked up 
     py_modules=['gpuadder'], 
     package_dir={'': 'src'}, 

     ext_modules = [ext], 

     # inject our custom trigger 
     cmdclass={'build_ext': custom_build_ext}, 

     # since the package has c code, the egg cannot be zipped 
     zip_safe=False)