相关疑难解决方法(0)

我一直在尝试优化一段涉及大型多维数组计算的python代码.我对numba的结果有违反直觉.我正在运行MBP,2015年中期,2.5 GHz i7 quadcore,OS 10.10.5,python 2.7.11.考虑以下:

 import numpy as np
 from numba import jit, vectorize, guvectorize
 import numexpr as ne
 import timeit

 def add_two_2ds_naive(A,B,res):
     for i in range(A.shape[0]):
         for j in range(B.shape[1]):
             res[i,j] = A[i,j]+B[i,j]

 @jit
 def add_two_2ds_jit(A,B,res):
     for i in range(A.shape[0]):
         for j in range(B.shape[1]):
             res[i,j] = A[i,j]+B[i,j]

 @guvectorize(['float64[:,:],float64[:,:],float64[:,:]'],
    '(n,m),(n,m)->(n,m)',target='cpu')
 def add_two_2ds_cpu(A,B,res):
     for i in range(A.shape[0]):
         for j in range(B.shape[1]):
             res[i,j] = A[i,j]+B[i,j]

 @guvectorize(['(float64[:,:],float64[:,:],float64[:,:])'],
    '(n,m),(n,m)->(n,m)',target='parallel')
 def add_two_2ds_parallel(A,B,res):
     for i in range(A.shape[0]):
         for j in range(B.shape[1]):
             res[i,j] = A[i,j]+B[i,j]

 def …