Numba代码比纯python慢

我一直在努力加快粒子滤波器的重采样计算.由于python有很多方法可以加速它,我虽然会尝试所有这些.不幸的是,numba版本非常慢.由于Numba应该加速,我认为这是我的错误.

我尝试了4个不同的版本:

Numba

蟒蛇

NumPy的

用Cython

每个代码如下:

import numpy as np
import scipy as sp
import numba as nb
from cython_resample import cython_resample

@nb.autojit
def numba_resample(qs, xs, rands):
    n = qs.shape[0]
    lookup = np.cumsum(qs)
    results = np.empty(n)

    for j in range(n):
        for i in range(n):
            if rands[j] < lookup[i]:
                results[j] = xs[i]
                break
    return results

def python_resample(qs, xs, rands):
    n = qs.shape[0]
    lookup = np.cumsum(qs)
    results = np.empty(n)

    for j in range(n):
        for i in range(n):
            if rands[j] < lookup[i]:
                results[j] = xs[i]
                break
    return results

def numpy_resample(qs, xs, rands):
    results = np.empty_like(qs)
    lookup = sp.cumsum(qs)
    for j, key in enumerate(rands):
        i = sp.argmax(lookup>key)
        results[j] = xs[i]
    return results

#The following is the code for the cython module. It was compiled in a
#separate file, but is included here to aid in the question.
"""
import numpy as np
cimport numpy as np
cimport cython

DTYPE = np.float64

ctypedef np.float64_t DTYPE_t

@cython.boundscheck(False)
def cython_resample(np.ndarray[DTYPE_t, ndim=1] qs, 
             np.ndarray[DTYPE_t, ndim=1] xs, 
             np.ndarray[DTYPE_t, ndim=1] rands):
    if qs.shape[0] != xs.shape[0] or qs.shape[0] != rands.shape[0]:
        raise ValueError("Arrays must have same shape")
    assert qs.dtype == xs.dtype == rands.dtype == DTYPE

    cdef unsigned int n = qs.shape[0]
    cdef unsigned int i, j 
    cdef np.ndarray[DTYPE_t, ndim=1] lookup = np.cumsum(qs)
    cdef np.ndarray[DTYPE_t, ndim=1] results = np.zeros(n, dtype=DTYPE)

    for j in range(n):
        for i in range(n):
            if rands[j] < lookup[i]:
                results[j] = xs[i]
                break
    return results
"""

if __name__ == '__main__':
    n = 100
    xs = np.arange(n, dtype=np.float64)
    qs = np.array([1.0/n,]*n)
    rands = np.random.rand(n)

    print "Timing Numba Function:"
    %timeit numba_resample(qs, xs, rands)
    print "Timing Python Function:"
    %timeit python_resample(qs, xs, rands)
    print "Timing Numpy Function:"
    %timeit numpy_resample(qs, xs, rands)
    print "Timing Cython Function:"
    %timeit cython_resample(qs, xs, rands)

这导致以下输出:

Timing Numba Function:
1 loops, best of 3: 8.23 ms per loop
Timing Python Function:
100 loops, best of 3: 2.48 ms per loop
Timing Numpy Function:
1000 loops, best of 3: 793 µs per loop
Timing Cython Function:
10000 loops, best of 3: 25 µs per loop

知道为什么numba代码如此之慢？我认为它至少可以与Numpy相媲美.

注意:如果有人对如何加速Numpy或Cython代码示例有任何想法,那也不错:)我的主要问题是关于Numba.