我遇到了一个非常奇怪的结果基准 http://nbviewer.ipython.org/github/rasbt/One-Python-benchmark-per-day/blob/master/ipython_nbs/day4_python_cython_numba.ipynb?create=1
这些都是冒泡排序实现的不同风格,n=10^4 时最快的方法是在内部将 Python 列表转换为 C 数组。相反,黄线对应于我将 NumPy 数组与内存视图一起使用的代码。我预计结果会是相反的。我(和同事)重复了几次基准测试,但总是得到相同的结果。也许有人知道这里发生了什么......
图中的黑线对应于代码:
%%cython
cimport cython
from libc.stdlib cimport malloc, free
def cython_bubblesort_clist(a_list):
"""
The Cython implementation of bubble sort with internal
conversion between Python list objects and C arrays.
"""
cdef int *c_list
c_list = <int *>malloc(len(a_list)*cython.sizeof(int))
cdef int count, i, j # static type declarations
count = len(a_list)
# convert Python list to C array
for i in range(count):
c_list[i] = a_list[i]
for i in range(count):
for j in range(1, count):
if c_list[j] < c_list[j-1]:
c_list[j-1], c_list[j] = c_list[j], c_list[j-1]
# convert C array back to Python list
for i in range(count):
a_list[i] = c_list[i]
free(c_list)
return a_list
以及这段代码的粉色线:
%%cython
import numpy as np
cimport numpy as np
cimport cython
def cython_bubblesort_numpy(long[:] np_ary):
"""
The Cython implementation of bubble sort with NumPy memoryview.
"""
cdef int count, i, j # static type declarations
count = np_ary.shape[0]
for i in range(count):
for j in range(1, count):
if np_ary[j] < np_ary[j-1]:
np_ary[j-1], np_ary[j] = np_ary[j], np_ary[j-1]
return np.asarray(np_ary)