到目前为止，我尝试过的最快的方法是基于Python烹饪书erat2函数:

import itertools as it
def erat2a( ):
    D = {  }
    yield 2
    for q in it.islice(it.count(3), 0, None, 2):
        p = D.pop(q, None)
        if p is None:
            D[q*q] = q
            yield q
        else:
            x = q + 2*p
            while x in D:
                x += 2*p
            D[x] = p

关于加速的解释，请看下面的答案。

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]

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

如果你接受itertools，但不接受numpy，这里有一个针对Python 3的rwh_primes2的改编版本，它在我的机器上运行速度大约是原来的两倍。唯一的实质性变化是使用bytearray而不是列表来表示布尔值，并使用压缩而不是列表推导来构建最终列表。(如果可以的话，我会把这句话作为moarningsun之类的评论。)

import itertools
izip = itertools.zip_longest
chain = itertools.chain.from_iterable
compress = itertools.compress
def rwh_primes2_python3(n):
    """ Input n>=6, Returns a list of primes, 2 <= p < n """
    zero = bytearray([False])
    size = n//3 + (n % 6 == 2)
    sieve = bytearray([True]) * size
    sieve[0] = False
    for i in range(int(n**0.5)//3+1):
      if sieve[i]:
        k=3*i+1|1
        start = (k*k+4*k-2*k*(i&1))//3
        sieve[(k*k)//3::2*k]=zero*((size - (k*k)//3 - 1) // (2 * k) + 1)
        sieve[  start ::2*k]=zero*((size -   start  - 1) // (2 * k) + 1)
    ans = [2,3]
    poss = chain(izip(*[range(i, n, 6) for i in (1,5)]))
    ans.extend(compress(poss, sieve))
    return ans

比较:

>>> timeit.timeit('primes.rwh_primes2(10**6)', setup='import primes', number=1)
0.0652179726976101
>>> timeit.timeit('primes.rwh_primes2_python3(10**6)', setup='import primes', number=1)
0.03267321276325674

and

>>> timeit.timeit('primes.rwh_primes2(10**8)', setup='import primes', number=1)
6.394284538007014
>>> timeit.timeit('primes.rwh_primes2_python3(10**8)', setup='import primes', number=1)
3.833829450302801

下面是Eratosthenes的一个numpy版本，具有良好的复杂度(低于排序长度为n的数组)和向量化。与@unutbu相比，用46微秒就可以找到100万以下的所有质数。

import numpy as np 
def generate_primes(n):
    is_prime = np.ones(n+1,dtype=bool)
    is_prime[0:2] = False
    for i in range(int(n**0.5)+1):
        if is_prime[i]:
            is_prime[i**2::i]=False
    return np.where(is_prime)[0]

计时:

import time    
for i in range(2,10):
    timer =time.time()
    generate_primes(10**i)
    print('n = 10^',i,' time =', round(time.time()-timer,6))

>> n = 10^ 2  time = 5.6e-05
>> n = 10^ 3  time = 6.4e-05
>> n = 10^ 4  time = 0.000114
>> n = 10^ 5  time = 0.000593
>> n = 10^ 6  time = 0.00467
>> n = 10^ 7  time = 0.177758
>> n = 10^ 8  time = 1.701312
>> n = 10^ 9  time = 19.322478

随着时间的推移，我收集了几个质数筛子。我电脑上最快的是这样的:

from time import time
# 175 ms for all the primes up to the value 10**6
def primes_sieve(limit):
    a = [True] * limit
    a[0] = a[1] = False
    #a[2] = True
    for n in xrange(4, limit, 2):
        a[n] = False
    root_limit = int(limit**.5)+1
    for i in xrange(3,root_limit):
        if a[i]:
            for n in xrange(i*i, limit, 2*i):
                a[n] = False
    return a

LIMIT = 10**6
s=time()
primes = primes_sieve(LIMIT)
print time()-s