1、下载vs2017，选择安装C++和python的开发工具
添加环境变量中 添加path，vs2017 的cl.exe的全路径

2、到python官网下载python3或者2，安装。建议使用anaconda进行python 的管理。

3、到CUDA官网下载CUDA，除自动添加的path外，添加新的path
CUDA_SDK_PATH = C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.2
CUDA_LIB_PATH = %CUDA_PATH%\lib\x64
CUDA_BIN_PATH = %CUDA_PATH%\bin
CUDA_SDK_BIN_PATH = %CUDA_SDK_PATH%\bin\win64
CUDA_SDK_LIB_PATH = %CUDA_SDK_PATH%\common\lib\x64
4、下载PyCuda
https://www.lfd.uci.edu/~gohlke/pythonlibs/?cm_mc_uid=08085305845514542921829&cm_mc_sid_50200000=1456395916#pycuda
选择对应版本,cp代表python版本，然后安装

pip install pycuda-2015.1.3+cuda7518-cp35-none-win_amd64.whl

5、vs2017测试
代码：

import pycuda.autoinit
import pycuda.driver as drv
import numpy
 
from pycuda.compiler import SourceModule
mod = SourceModule("""
__global__ void multiply_them(float *dest, float *a, float *b)
{
  const int i = threadIdx.x;
  dest[i] = a[i] * b[i];
}
""")
 
multiply_them = mod.get_function("multiply_them")
 
a = numpy.random.randn(400).astype(numpy.float32)
b = numpy.random.randn(400).astype(numpy.float32)
 
dest = numpy.zeros_like(a)
multiply_them(
        drv.Out(dest), drv.In(a), drv.In(b),
        block=(400,1,1), grid=(1,1))
 
print ( dest-a*b )

输出：