假设N < 9,080,191, Miller-Rabin's Primality检验的确定性实现

import sys

def miller_rabin_pass(a, n):
    d = n - 1
    s = 0
    while d % 2 == 0:
        d >>= 1
        s += 1

    a_to_power = pow(a, d, n)
    if a_to_power == 1:
        return True
    for i in range(s-1):
        if a_to_power == n - 1:
            return True
        a_to_power = (a_to_power * a_to_power) % n
    return a_to_power == n - 1


def miller_rabin(n):
    if n <= 2:
        return n == 2

    if n < 2_047:
        return miller_rabin_pass(2, n)

    return all(miller_rabin_pass(a, n) for a in (31, 73))


n = int(sys.argv[1])
primes = [2]
for p in range(3,n,2):
  if miller_rabin(p):
    primes.append(p)
print len(primes)

根据维基百科(http://en.wikipedia.org/wiki/Miller -Rabin_primality_test)上的文章，对于a = 37和73，测试N < 9,080,191足以判断N是否为合数。

我从原始米勒-拉宾测试的概率实现中改编了源代码:https://www.literateprograms.org/miller-rabin_primality_test__python_.html

对于最快的代码，numpy解决方案是最好的。不过，出于纯粹的学术原因，我发布了我的纯python版本，它比上面发布的食谱版本快不到50%。由于我将整个列表放在内存中，所以需要足够的空间来容纳所有内容，但它的可伸缩性似乎相当好。

def daniel_sieve_2(maxNumber):
    """
    Given a number, returns all numbers less than or equal to
    that number which are prime.
    """
    allNumbers = range(3, maxNumber+1, 2)
    for mIndex, number in enumerate(xrange(3, maxNumber+1, 2)):
        if allNumbers[mIndex] == 0:
            continue
        # now set all multiples to 0
        for index in xrange(mIndex+number, (maxNumber-3)/2+1, number):
            allNumbers[index] = 0
    return [2] + filter(lambda n: n!=0, allNumbers)

结果是:

>>>mine = timeit.Timer("daniel_sieve_2(1000000)",
...                    "from sieves import daniel_sieve_2")
>>>prev = timeit.Timer("get_primes_erat(1000000)",
...                    "from sieves import get_primes_erat")
>>>print "Mine: {0:0.4f} ms".format(min(mine.repeat(3, 1))*1000)
Mine: 428.9446 ms
>>>print "Previous Best {0:0.4f} ms".format(min(prev.repeat(3, 1))*1000)
Previous Best 621.3581 ms

第一次使用python，所以我在这里使用的一些方法可能看起来有点麻烦。我只是直接将我的c++代码转换为python，这就是我所拥有的(尽管在python中有点慢)

#!/usr/bin/env python
import time

def GetPrimes(n):

    Sieve = [1 for x in xrange(n)]

    Done = False
    w = 3

    while not Done:

        for q in xrange (3, n, 2):
            Prod = w*q
            if Prod < n:
                Sieve[Prod] = 0
            else:
                break

        if w > (n/2):
            Done = True
        w += 2

    return Sieve



start = time.clock()

d = 10000000
Primes = GetPrimes(d)

count = 1 #This is for 2

for x in xrange (3, d, 2):
    if Primes[x]:
        count+=1

elapsed = (time.clock() - start)
print "\nFound", count, "primes in", elapsed, "seconds!\n"

pythonw Primes.py 在12.799119秒内找到664579个质数!

#!/usr/bin/env python
import time

def GetPrimes2(n):

    Sieve = [1 for x in xrange(n)]

    for q in xrange (3, n, 2):
        k = q
        for y in xrange(k*3, n, k*2):
            Sieve[y] = 0

    return Sieve



start = time.clock()

d = 10000000
Primes = GetPrimes2(d)

count = 1 #This is for 2

for x in xrange (3, d, 2):
    if Primes[x]:
        count+=1

elapsed = (time.clock() - start)
print "\nFound", count, "primes in", elapsed, "seconds!\n"

pythonw Primes2.py 在10.230172秒内找到664579个质数!

#!/usr/bin/env python
import time

def GetPrimes3(n):

    Sieve = [1 for x in xrange(n)]

    for q in xrange (3, n, 2):
        k = q
        for y in xrange(k*k, n, k << 1):
            Sieve[y] = 0

    return Sieve



start = time.clock()

d = 10000000
Primes = GetPrimes3(d)

count = 1 #This is for 2

for x in xrange (3, d, 2):
    if Primes[x]:
        count+=1

elapsed = (time.clock() - start)
print "\nFound", count, "primes in", elapsed, "seconds!\n"

python Primes2.py 在7.113776秒内找到664579个质数!

我很惊讶居然没人提到numba。

该版本在2.47 ms±36.5µs内达到1M标记。

几年前，维基百科页面上出现了一个阿特金筛子的伪代码。这已经不存在了，参考阿特金筛似乎是一个不同的算法。一个2007/03/01版本的维基百科页面(Primer number as 2007-03-01)显示了我用作参考的伪代码。

import numpy as np
from numba import njit

@njit
def nb_primes(n):
    # Generates prime numbers 2 <= p <= n
    # Atkin's sieve -- see https://en.wikipedia.org/w/index.php?title=Prime_number&oldid=111775466
    sqrt_n = int(np.sqrt(n)) + 1

    # initialize the sieve
    s = np.full(n + 1, -1, dtype=np.int8)
    s[2] = 1
    s[3] = 1

    # put in candidate primes:
    # integers which have an odd number of
    # representations by certain quadratic forms
    for x in range(1, sqrt_n):
        x2 = x * x
        for y in range(1, sqrt_n):
            y2 = y * y
            k = 4 * x2 + y2
            if k <= n and (k % 12 == 1 or k % 12 == 5): s[k] *= -1
            k = 3 * x2 + y2
            if k <= n and (k % 12 == 7): s[k] *= -1
            k = 3 * x2 - y2
            if k <= n and x > y and k % 12 == 11: s[k] *= -1

    # eliminate composites by sieving
    for k in range(5, sqrt_n):
        if s[k]:
            k2 = k*k
            # k is prime, omit multiples of its square; this is sufficient because
            # composites which managed to get on the list cannot be square-free
            for i in range(1, n // k2 + 1):
                j = i * k2 # j ∈ {k², 2k², 3k², ..., n}
                s[j] = -1
    return np.nonzero(s>0)[0]

# initial run for "compilation" 
nb_primes(10)

时机

In[10]:
%timeit nb_primes(1_000_000)

Out[10]:
2.47 ms ± 36.5 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

In[11]:
%timeit nb_primes(10_000_000)

Out[11]:
33.4 ms ± 373 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)

In[12]:
%timeit nb_primes(100_000_000)

Out[12]:
828 ms ± 5.64 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

我对这个问题反应迟钝，但这似乎是一个有趣的练习。我使用numpy，这可能是作弊，我怀疑这个方法是最快的，但它应该是清楚的。它筛选一个仅引用其下标的布尔数组，并从所有True值的下标中引出质数。不需要取模。

import numpy as np
def ajs_primes3a(upto):
    mat = np.ones((upto), dtype=bool)
    mat[0] = False
    mat[1] = False
    mat[4::2] = False
    for idx in range(3, int(upto ** 0.5)+1, 2):
        mat[idx*2::idx] = False
    return np.where(mat == True)[0]

这里有一个来自Python Cookbook的非常简洁的示例——该URL的最快版本是:

import itertools
def erat2( ):
    D = {  }
    yield 2
    for q in itertools.islice(itertools.count(3), 0, None, 2):
        p = D.pop(q, None)
        if p is None:
            D[q*q] = q
            yield q
        else:
            x = p + q
            while x in D or not (x&1):
                x += p
            D[x] = p

这就给出了

def get_primes_erat(n):
  return list(itertools.takewhile(lambda p: p<n, erat2()))

在shell提示符(正如我喜欢做的那样)中测量这段代码在pri.py中，我观察到:

$ python2.5 -mtimeit -s'import pri' 'pri.get_primes(1000000)'
10 loops, best of 3: 1.69 sec per loop
$ python2.5 -mtimeit -s'import pri' 'pri.get_primes_erat(1000000)'
10 loops, best of 3: 673 msec per loop

所以看起来食谱解决方案的速度是原来的两倍多。