Question

我正在尝试编译并运行CUDA脚本。

我的环境是：

C:\Temp\CUDA>python --version
Python 3.6.3 :: Anaconda custom (64-bit)

C:\Temp\CUDA>python --version accelerate
Python 3.6.3 :: Anaconda custom (64-bit)

C:\Temp\CUDA>python --version cuda_toolki
Python 3.6.3 :: Anaconda custom (64-bit)

我正在尝试编译的python脚本是：

from numba.pycc import CC
import numpy as np
import time

cc = CC('VectorAdd')

def VectorAdd(a, b):
    return a + b

def main():
    N = 32000000

    A = np.ones(N, dtype=np.float32)
    B = np.ones(N, dtype=np.float32)

    start = time.time()
    C = VectorAdd(A, B)
    vector_add_time = time.time() - start

    print("C[:5] = " + str(C[:5]))
    print("C[-5:] = " + str(C[-5:]))
    print("VectorAdd took % seconds" % vector_add_time)

if __name__ == '__main__':
    cc.compile()

这产生了文件：

VectorAddcp36-win-amd64.pyd

在我的目录中。然后我运行了脚本：

import VectorAdd

def main():
    VectorAdd.main()

if __name__ == '__main__':
    main()

执行main方法，我得到了：

C:\Temp\CUDA>python VectorAdd_run_pyd.py
Traceback (most recent call last):
  File "VectorAdd_run_pyd.py", line 7, in <module>
    main()
  File "VectorAdd_run_pyd.py", line 4, in main
    VectorAdd.main()
AttributeError: module 'VectorAdd' has no attribute 'main'

我做错了什么？

查尔斯

调用编译的cuda python脚本时出错

0 个答案: