我有 CUDA 代码,我想使用 distutils 为 Python 构建一个动态库。但即使安装了“nvcc”编译器,distutils 似乎也无法识别“.cu”文件。不知道如何完成它。
问问题
5199 次
2 回答
18
Distutils 默认无法编译 CUDA,因为它不支持同时使用多个编译器。默认情况下,它仅根据您的平台设置为编译器,而不是根据您拥有的源代码类型。
我在 github 上有一个示例项目,其中包含一些猴子补丁到 distutils 中,以支持这一点。示例项目是一个 C++ 类,它管理一些 GPU 内存和一个 CUDA 内核,包装在 swig 中,并且全部使用python setup.py install
. 重点是数组操作,所以我们也在使用 numpy。内核对这个示例项目所做的所有事情就是将数组中的每个元素加一。
代码在这里:https ://github.com/rmcgibbo/npcuda-example 。这是 setup.py 脚本。整个代码的关键是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)
于 2012-11-09T01:13:26.343 回答
2
作为distutils
/的替代方案setuptools
,您可以使用scikit-build
(与CMakeLists.txt
、pyproject.toml
和setup.cfg
/一起setup.py
):
import sys
from pathlib import Path
from skbuild import setup
from setuptools import find_packages
# https://github.com/scikit-build/scikit-build/issues/521#issuecomment-753035688
for i in (Path(__file__).resolve().parent / "_skbuild").rglob("CMakeCache.txt"):
i.write_text(re.sub("^//.*$\n^[^#].*pip-build-env.*$", "", i.read_text(), flags=re.M))
setup(cmake_args=[f"-DPython3_ROOT_DIR={sys.prefix}"],
packages=find_packages(exclude=["tests"]))
于 2021-02-01T22:48:07.450 回答