在这里寻找答案。
基本思想是你想要cpython.array.array
和cpython.array.clone
(不是 cython.array.*
):
from cpython.array cimport array, clone
# This type is what you want and can be cast to things of
# the "double[:]" syntax, so no problems there
cdef array[double] armv, templatemv
templatemv = array('d')
# This is fast
armv = clone(templatemv, L, False)
编辑
事实证明,该线程中的基准是垃圾。这是我的设置,我的时间安排:
# cython: language_level=3
# cython: boundscheck=False
# cython: wraparound=False
import time
import sys
from cpython.array cimport array, clone
from cython.view cimport array as cvarray
from libc.stdlib cimport malloc, free
import numpy as numpy
cimport numpy as numpy
cdef int loops
def timefunc(name):
def timedecorator(f):
cdef int L, i
print("Running", name)
for L in [1, 10, 100, 1000, 10000, 100000, 1000000]:
start = time.clock()
f(L)
end = time.clock()
print(format((end-start) / loops * 1e6, "2f"), end=" ")
sys.stdout.flush()
print("μs")
return timedecorator
print()
print("INITIALISATIONS")
loops = 100000
@timefunc("cpython.array buffer")
def _(int L):
cdef int i
cdef array[double] arr, template = array('d')
for i in range(loops):
arr = clone(template, L, False)
# Prevents dead code elimination
str(arr[0])
@timefunc("cpython.array memoryview")
def _(int L):
cdef int i
cdef double[::1] arr
cdef array template = array('d')
for i in range(loops):
arr = clone(template, L, False)
# Prevents dead code elimination
str(arr[0])
@timefunc("cpython.array raw C type")
def _(int L):
cdef int i
cdef array arr, template = array('d')
for i in range(loops):
arr = clone(template, L, False)
# Prevents dead code elimination
str(arr[0])
@timefunc("numpy.empty_like memoryview")
def _(int L):
cdef int i
cdef double[::1] arr
template = numpy.empty((L,), dtype='double')
for i in range(loops):
arr = numpy.empty_like(template)
# Prevents dead code elimination
str(arr[0])
@timefunc("malloc")
def _(int L):
cdef int i
cdef double* arrptr
for i in range(loops):
arrptr = <double*> malloc(sizeof(double) * L)
free(arrptr)
# Prevents dead code elimination
str(arrptr[0])
@timefunc("malloc memoryview")
def _(int L):
cdef int i
cdef double* arrptr
cdef double[::1] arr
for i in range(loops):
arrptr = <double*> malloc(sizeof(double) * L)
arr = <double[:L]>arrptr
free(arrptr)
# Prevents dead code elimination
str(arr[0])
@timefunc("cvarray memoryview")
def _(int L):
cdef int i
cdef double[::1] arr
for i in range(loops):
arr = cvarray((L,),sizeof(double),'d')
# Prevents dead code elimination
str(arr[0])
print()
print("ITERATING")
loops = 1000
@timefunc("cpython.array buffer")
def _(int L):
cdef int i
cdef array[double] arr = clone(array('d'), L, False)
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
# Prevents dead-code elimination
str(d)
@timefunc("cpython.array memoryview")
def _(int L):
cdef int i
cdef double[::1] arr = clone(array('d'), L, False)
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
# Prevents dead-code elimination
str(d)
@timefunc("cpython.array raw C type")
def _(int L):
cdef int i
cdef array arr = clone(array('d'), L, False)
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
# Prevents dead-code elimination
str(d)
@timefunc("numpy.empty_like memoryview")
def _(int L):
cdef int i
cdef double[::1] arr = numpy.empty((L,), dtype='double')
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
# Prevents dead-code elimination
str(d)
@timefunc("malloc")
def _(int L):
cdef int i
cdef double* arrptr = <double*> malloc(sizeof(double) * L)
cdef double d
for i in range(loops):
for i in range(L):
d = arrptr[i]
free(arrptr)
# Prevents dead-code elimination
str(d)
@timefunc("malloc memoryview")
def _(int L):
cdef int i
cdef double* arrptr = <double*> malloc(sizeof(double) * L)
cdef double[::1] arr = <double[:L]>arrptr
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
free(arrptr)
# Prevents dead-code elimination
str(d)
@timefunc("cvarray memoryview")
def _(int L):
cdef int i
cdef double[::1] arr = cvarray((L,),sizeof(double),'d')
cdef double d
for i in range(loops):
for i in range(L):
d = arr[i]
# Prevents dead-code elimination
str(d)
输出:
INITIALISATIONS
Running cpython.array buffer
0.100040 0.097140 0.133110 0.121820 0.131630 0.108420 0.112160 μs
Running cpython.array memoryview
0.339480 0.333240 0.378790 0.445720 0.449800 0.414280 0.414060 μs
Running cpython.array raw C type
0.048270 0.049250 0.069770 0.074140 0.076300 0.060980 0.060270 μs
Running numpy.empty_like memoryview
1.006200 1.012160 1.128540 1.212350 1.250270 1.235710 1.241050 μs
Running malloc
0.021850 0.022430 0.037240 0.046260 0.039570 0.043690 0.030720 μs
Running malloc memoryview
1.640200 1.648000 1.681310 1.769610 1.755540 1.804950 1.758150 μs
Running cvarray memoryview
1.332330 1.353910 1.358160 1.481150 1.517690 1.485600 1.490790 μs
ITERATING
Running cpython.array buffer
0.010000 0.027000 0.091000 0.669000 6.314000 64.389000 635.171000 μs
Running cpython.array memoryview
0.013000 0.015000 0.058000 0.354000 3.186000 33.062000 338.300000 μs
Running cpython.array raw C type
0.014000 0.146000 0.979000 9.501000 94.160000 916.073000 9287.079000 μs
Running numpy.empty_like memoryview
0.042000 0.020000 0.057000 0.352000 3.193000 34.474000 333.089000 μs
Running malloc
0.002000 0.004000 0.064000 0.367000 3.599000 32.712000 323.858000 μs
Running malloc memoryview
0.019000 0.032000 0.070000 0.356000 3.194000 32.100000 327.929000 μs
Running cvarray memoryview
0.014000 0.026000 0.063000 0.351000 3.209000 32.013000 327.890000 μs
(“迭代”基准的原因是某些方法在这方面具有惊人的不同特征。)
按初始化速度排序:
malloc
: 这是一个严酷的世界,但它很快。如果您需要分配很多东西并具有不受阻碍的迭代和索引性能,那就必须这样做。但通常你是一个不错的选择...
cpython.array raw C type
: 妈的,很快。而且是安全的。不幸的是,它通过 Python 访问其数据字段。您可以使用一个绝妙的技巧来避免这种情况:
arr.data.as_doubles[i]
在消除安全性的同时使其达到标准速度!这使它成为一个很好的替代品malloc
,基本上是一个非常参考计数的版本!
cpython.array buffer
: 安装时间仅为 的三到四倍malloc
,这看起来是个不错的选择。不幸的是,它有很大的开销(尽管与boundscheck
andwraparound
指令相比很小)。这意味着它只能与完全安全的变体竞争,但它是初始化速度最快的变体。你的选择。
cpython.array memoryview
:这现在比malloc
初始化慢一个数量级。这很遗憾,但它的迭代速度同样快。这是我建议的标准解决方案,除非boundscheck
或wraparound
启用(在这种情况下cpython.array buffer
可能是更引人注目的权衡)。
其余的部分。唯一值得一提的是numpy
's,因为对象附带了许多有趣的方法。不过,就是这样。