python distutils可以編譯CUDA代碼嗎？

Question

我有我想建立使用distutils的動態庫到Python代碼CUDA。但是，即使安裝了「nvcc」編譯器，distutils似乎也無法識別「.cu」文件。不知道如何完成它。

Answer 1

的Distutils不能默認編譯CUDA，因爲它不會同時使用多個編譯器支持。默認情況下，它會根據您的平臺設置爲編譯器，而不是您擁有的源代碼類型。

我有一個包含一些猴子補丁到的distutils在這種支持砍在github的示例項目。示例項目是管理一些GPU內存和CUDA核心，包裹在痛飲，和所有剛剛python setup.py install編譯的C++類。重點是數組操作，所以我們也使用numpy。所有內核都爲此示例項目增加一個數組中的每個元素。

的代碼是在這裏：https://github.com/rmcgibbo/npcuda-example。這是setup.py腳本。整個代碼的關鍵是customize_compiler_for_nvcc()。

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)