python矩阵运算速度_用numpy矩阵加速计算

如果你的比特真的是每字节8个/32个整型，

您可以将smallMatrix缩小到20x16，

然后尝试以下方法，在这里只做一行。

(newMatrix[x, y] = 1当x周围20x16的任何一个位y是1？？

你到底在找什么？)在python -m timeit -s '

""" slide 16-bit mask across 32-bit pairs bits[j], bits[j+1] """

import numpy as np

bits = np.zeros( 2000 // 16, np.uint16 ) # 2000 bits

bits[::8] = 1

mask = 32+16

nhit = 16 * [0]

def hit16( bits, mask, nhit ):

"""

slide 16-bit mask across 32-bit pairs bits[j], bits[j+1]

bits: long np.array( uint16 )

mask: 16 bits, int

out: nhit[j] += 1 where pair & mask != 0

"""

left = bits[0]

for b in bits[1:]:

pair = (left << 16) | b

if pair: # np idiom for non-0 words ?

m = mask

for j in range(16):

if pair & m:

nhit[j] += 1

# hitposition = jb*16 + j

m <<= 1

left = b

# if any(nhit): print "hit16:", nhit

' \

'

hit16( bits, mask, nhit )

'

# 15 msec per loop, bits[::4] = 1

# 11 msec per loop, bits[::8] = 1

# mac g4 ppc