我把Project Euler中的第12题作为一个编程练习,并比较了我在C、Python、Erlang和Haskell中的实现(当然不是最优的)。为了获得更高的执行时间,我搜索第一个因数超过1000的三角形数,而不是原始问题中所述的500。

结果如下:

C:

lorenzo@enzo:~/erlang$ gcc -lm -o euler12.bin euler12.c
lorenzo@enzo:~/erlang$ time ./euler12.bin
842161320

real    0m11.074s
user    0m11.070s
sys 0m0.000s

Python:

lorenzo@enzo:~/erlang$ time ./euler12.py 
842161320

real    1m16.632s
user    1m16.370s
sys 0m0.250s

Python与PyPy:

lorenzo@enzo:~/Downloads/pypy-c-jit-43780-b590cf6de419-linux64/bin$ time ./pypy /home/lorenzo/erlang/euler12.py 
842161320

real    0m13.082s
user    0m13.050s
sys 0m0.020s

Erlang:

lorenzo@enzo:~/erlang$ erlc euler12.erl 
lorenzo@enzo:~/erlang$ time erl -s euler12 solve
Erlang R13B03 (erts-5.7.4) [source] [64-bit] [smp:4:4] [rq:4] [async-threads:0] [hipe] [kernel-poll:false]

Eshell V5.7.4  (abort with ^G)
1> 842161320

real    0m48.259s
user    0m48.070s
sys 0m0.020s

Haskell:

lorenzo@enzo:~/erlang$ ghc euler12.hs -o euler12.hsx
[1 of 1] Compiling Main             ( euler12.hs, euler12.o )
Linking euler12.hsx ...
lorenzo@enzo:~/erlang$ time ./euler12.hsx 
842161320

real    2m37.326s
user    2m37.240s
sys 0m0.080s

简介:

C: 100% Python: 692% (PyPy占118%) Erlang: 436%(135%归功于RichardC) Haskell: 1421%

我认为C语言有一个很大的优势,因为它使用长来进行计算,而不是像其他三种那样使用任意长度的整数。它也不需要首先加载运行时(其他的呢?)

问题1: Erlang, Python和Haskell是否会因为使用任意长度的整数而降低速度,或者只要值小于MAXINT就不会?

问题2: 哈斯克尔为什么这么慢?是否有一个编译器标志关闭刹车或它是我的实现?(后者是很有可能的,因为Haskell对我来说是一本有七个印章的书。)

问题3: 你能否给我一些提示,如何在不改变我确定因素的方式的情况下优化这些实现?以任何方式优化:更好、更快、更“原生”的语言。

编辑:

问题4: 我的函数实现是否允许LCO(最后调用优化,也就是尾递归消除),从而避免在调用堆栈中添加不必要的帧?

虽然我不得不承认我的Haskell和Erlang知识非常有限,但我确实试图用这四种语言实现尽可能相似的相同算法。


使用的源代码:

#include <stdio.h>
#include <math.h>

int factorCount (long n)
{
    double square = sqrt (n);
    int isquare = (int) square;
    int count = isquare == square ? -1 : 0;
    long candidate;
    for (candidate = 1; candidate <= isquare; candidate ++)
        if (0 == n % candidate) count += 2;
    return count;
}

int main ()
{
    long triangle = 1;
    int index = 1;
    while (factorCount (triangle) < 1001)
    {
        index ++;
        triangle += index;
    }
    printf ("%ld\n", triangle);
}

#! /usr/bin/env python3.2

import math

def factorCount (n):
    square = math.sqrt (n)
    isquare = int (square)
    count = -1 if isquare == square else 0
    for candidate in range (1, isquare + 1):
        if not n % candidate: count += 2
    return count

triangle = 1
index = 1
while factorCount (triangle) < 1001:
    index += 1
    triangle += index

print (triangle)

-module (euler12).
-compile (export_all).

factorCount (Number) -> factorCount (Number, math:sqrt (Number), 1, 0).

factorCount (_, Sqrt, Candidate, Count) when Candidate > Sqrt -> Count;

factorCount (_, Sqrt, Candidate, Count) when Candidate == Sqrt -> Count + 1;

factorCount (Number, Sqrt, Candidate, Count) ->
    case Number rem Candidate of
        0 -> factorCount (Number, Sqrt, Candidate + 1, Count + 2);
        _ -> factorCount (Number, Sqrt, Candidate + 1, Count)
    end.

nextTriangle (Index, Triangle) ->
    Count = factorCount (Triangle),
    if
        Count > 1000 -> Triangle;
        true -> nextTriangle (Index + 1, Triangle + Index + 1)  
    end.

solve () ->
    io:format ("~p~n", [nextTriangle (1, 1) ] ),
    halt (0).

factorCount number = factorCount' number isquare 1 0 - (fromEnum $ square == fromIntegral isquare)
    where square = sqrt $ fromIntegral number
          isquare = floor square

factorCount' number sqrt candidate count
    | fromIntegral candidate > sqrt = count
    | number `mod` candidate == 0 = factorCount' number sqrt (candidate + 1) (count + 2)
    | otherwise = factorCount' number sqrt (candidate + 1) count

nextTriangle index triangle
    | factorCount triangle > 1000 = triangle
    | otherwise = nextTriangle (index + 1) (triangle + index + 1)

main = print $ nextTriangle 1 1

当前回答

看看这个博客。在过去一年左右的时间里,他用Haskell和Python完成了一些Project Euler问题,他通常发现Haskell要快得多。我认为在这些语言之间,它更多地与你的流畅性和编码风格有关。

说到Python速度,你使用了错误的实现!尝试一下PyPy,对于这样的事情,你会发现它要快得多。

其他回答

I made the assumption that the number of factors is only large if the numbers involved have many small factors. So I used thaumkid's excellent algorithm, but first used an approximation to the factor count that is never too small. It's quite simple: Check for prime factors up to 29, then check the remaining number and calculate an upper bound for the nmber of factors. Use this to calculate an upper bound for the number of factors, and if that number is high enough, calculate the exact number of factors.

下面的代码不需要这个假设来保证正确性,但是为了快速。这似乎很有效;只有大约十万分之一的数字给出了足够高的估计,需要进行全面检查。

代码如下:

// Return at least the number of factors of n.
static uint64_t approxfactorcount (uint64_t n)
{
    uint64_t count = 1, add;

#define CHECK(d)                            \
    do {                                    \
        if (n % d == 0) {                   \
            add = count;                    \
            do { n /= d; count += add; }    \
            while (n % d == 0);             \
        }                                   \
    } while (0)

    CHECK ( 2); CHECK ( 3); CHECK ( 5); CHECK ( 7); CHECK (11); CHECK (13);
    CHECK (17); CHECK (19); CHECK (23); CHECK (29);
    if (n == 1) return count;
    if (n < 1ull * 31 * 31) return count * 2;
    if (n < 1ull * 31 * 31 * 37) return count * 4;
    if (n < 1ull * 31 * 31 * 37 * 37) return count * 8;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41) return count * 16;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43) return count * 32;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47) return count * 64;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53) return count * 128;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53 * 59) return count * 256;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53 * 59 * 61) return count * 512;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53 * 59 * 61 * 67) return count * 1024;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53 * 59 * 61 * 67 * 71) return count * 2048;
    if (n < 1ull * 31 * 31 * 37 * 37 * 41 * 43 * 47 * 53 * 59 * 61 * 67 * 71 * 73) return count * 4096;
    return count * 1000000;
}

// Return the number of factors of n.
static uint64_t factorcount (uint64_t n)
{
    uint64_t count = 1, add;

    CHECK (2); CHECK (3);

    uint64_t d = 5, inc = 2;
    for (; d*d <= n; d += inc, inc = (6 - inc))
        CHECK (d);

    if (n > 1) count *= 2; // n must be a prime number
    return count;
}

// Prints triangular numbers with record numbers of factors.
static void printrecordnumbers (uint64_t limit)
{
    uint64_t record = 30000;

    uint64_t count1, factor1;
    uint64_t count2 = 1, factor2 = 1;

    for (uint64_t n = 1; n <= limit; ++n)
    {
        factor1 = factor2;
        count1 = count2;

        factor2 = n + 1; if (factor2 % 2 == 0) factor2 /= 2;
        count2 = approxfactorcount (factor2);

        if (count1 * count2 > record)
        {
            uint64_t factors = factorcount (factor1) * factorcount (factor2);
            if (factors > record)
            {
                printf ("%lluth triangular number = %llu has %llu factors\n", n, factor1 * factor2, factors);
                record = factors;
            }
        }
    }
}

其中,14753024个三角形数有13824个因子用时约0.7秒,879207615个三角形数有61440个因子用时34秒,12524486975个三角形数有138240个因子用时10分5秒,26467,792064个三角形数有172032个因子用时21分25秒(2.4GHz Core2 Duo),因此该代码平均每个数只需要116个处理器周期。最后一个三角数本身大于2^68,所以

问题1:erlang, python和haskell会因为使用任意长度的整数而降低速度吗?还是只要值小于MAXINT就不会?

This is unlikely. I cannot say much about Erlang and Haskell (well, maybe a bit about Haskell below) but I can point a lot of other bottlenecks in Python. Every time the program tries to execute an operation with some values in Python, it should verify whether the values are from the proper type, and it costs a bit of time. Your factorCount function just allocates a list with range (1, isquare + 1) various times, and runtime, malloc-styled memory allocation is way slower than iterating on a range with a counter as you do in C. Notably, the factorCount() is called multiple times and so allocates a lot of lists. Also, let us not forget that Python is interpreted and the CPython interpreter has no great focus on being optimized.

编辑:哦,好吧,我注意到你使用的是Python 3,所以range()不返回一个列表,而是一个生成器。在这种情况下,我关于分配列表的观点有一半是错误的:该函数只是分配范围对象,尽管效率很低,但没有分配包含很多项的列表那么低。

问题2:为什么haskell这么慢?是否有一个编译器标志关闭刹车或它是我的实现?(后者很有可能,因为haskell对我来说是一本有七个印章的书。)

你在使用Hugs吗?Hugs是一个相当慢的解释器。如果你正在使用它,也许你可以得到一个更好的GHC时间-但我只是在思考假设,这种东西,一个好的Haskell编译器做的是非常迷人的,远远超出我的理解:)

问题3:你能给我一些提示吗?如何在不改变我确定因素的方式的情况下优化这些实现?以任何方式优化:更好、更快、更“原生”的语言。

我得说你在玩一场不好笑的游戏。了解各种语言最好的部分是尽可能以不同的方式使用它们:)但我离题了,我只是对这一点没有任何建议。对不起,我希望有人能在这种情况下帮助你:)

问题4:我的函数实现是否允许LCO,从而避免在调用堆栈中添加不必要的帧?

据我所知,您只需要确保您的递归调用是返回值之前的最后一个命令。换句话说,像下面这样的函数可以使用这样的优化:

def factorial(n, acc=1):
    if n > 1:
        acc = acc * n
        n = n - 1
        return factorial(n, acc)
    else:
        return acc

然而,如果你的函数如下所示,你就不会有这样的优化,因为在递归调用之后有一个操作(乘法):

def factorial2(n):
    if n > 1:
        f = factorial2(n-1)
        return f*n
    else:
        return 1

我将操作分隔在一些局部变量中,以便明确执行哪些操作。然而,最常见的是看到这些函数如下所示,但它们对于我所说的观点是等价的:

def factorial(n, acc=1):
    if n > 1:
        return factorial(n-1, acc*n)
    else:
        return acc

def factorial2(n):
    if n > 1:
        return n*factorial(n-1)
    else:
        return 1

注意,这是由编译器/解释器来决定是否进行尾递归。例如,如果我记得很清楚,Python解释器就不会这样做(我在示例中使用Python只是因为它的语法流畅)。不管怎样,如果你发现了一些奇怪的东西,比如带两个参数的阶乘函数(其中一个参数有acc, accumulator等名称),现在你知道为什么人们这样做了:)

在Python优化方面,除了使用PyPy(对代码进行零更改即可获得令人印象深刻的加速)之外,还可以使用PyPy的翻译工具链编译与rpython兼容的版本,或者使用Cython构建扩展模块,在我的测试中,这两种工具都比C版本快,而Cython模块的速度几乎是C版本的两倍。作为参考,我包括C和PyPy基准测试结果:

C(编译gcc -O3 -lm)

% time ./euler12-c 
842161320

./euler12-c  11.95s 
 user 0.00s 
 system 99% 
 cpu 11.959 total

PyPy 1.5

% time pypy euler12.py
842161320
pypy euler12.py  
16.44s user 
0.01s system 
99% cpu 16.449 total

RPython(使用最新的PyPy修订版,c2f583445aee)

% time ./euler12-rpython-c
842161320
./euler12-rpy-c  
10.54s user 0.00s 
system 99% 
cpu 10.540 total

崇拜0.15

% time python euler12-cython.py
842161320
python euler12-cython.py  
6.27s user 0.00s 
system 99% 
cpu 6.274 total

RPython版本有几个关键的变化。要转换成一个独立的程序,您需要定义目标,在本例中是主函数。它被期望接受sys。Argv作为它唯一的参数,并且需要返回一个int。你可以使用translate.py, % translate.py euler12-rpython.py来翻译它,它可以翻译成C语言并为你编译它。

# euler12-rpython.py

import math, sys

def factorCount(n):
    square = math.sqrt(n)
    isquare = int(square)
    count = -1 if isquare == square else 0
    for candidate in xrange(1, isquare + 1):
        if not n % candidate: count += 2
    return count

def main(argv):
    triangle = 1
    index = 1
    while factorCount(triangle) < 1001:
        index += 1
        triangle += index
    print triangle
    return 0

if __name__ == '__main__':
    main(sys.argv)

def target(*args):
    return main, None

Cython版本被重写为扩展模块_euler12。我从一个普通的python文件中导入并调用它。_euler12。Pyx本质上与您的版本相同,只是有一些额外的静态类型声明。setup.py有一个正常的样板来构建扩展,使用python setup.py build_ext——inplace。

# _euler12.pyx
from libc.math cimport sqrt

cdef int factorCount(int n):
    cdef int candidate, isquare, count
    cdef double square
    square = sqrt(n)
    isquare = int(square)
    count = -1 if isquare == square else 0
    for candidate in range(1, isquare + 1):
        if not n % candidate: count += 2
    return count

cpdef main():
    cdef int triangle = 1, index = 1
    while factorCount(triangle) < 1001:
        index += 1
        triangle += index
    print triangle

# euler12-cython.py
import _euler12
_euler12.main()

# setup.py
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext

ext_modules = [Extension("_euler12", ["_euler12.pyx"])]

setup(
  name = 'Euler12-Cython',
  cmdclass = {'build_ext': build_ext},
  ext_modules = ext_modules
)

老实说,我对RPython或Cython都没有什么经验,对结果感到惊喜。如果您正在使用CPython,那么在Cython扩展模块中编写cpu密集型代码似乎是优化程序的一种非常简单的方法。

问题1:Erlang、Python和Haskell是否会因为使用 任意长度的整数,只要值更小 比MAXINT ?

对于Erlang,第一个问题的答案是否定的。最后一个问题可以通过适当地使用Erlang来回答,如下所示:

http://bredsaal.dk/learning-erlang-using-projecteuler-net

由于它比您最初的C示例要快,我猜它会有很多问题,因为其他人已经详细讨论过了。

这个Erlang模块在一个便宜的上网本上执行大约5秒…它使用erlang中的网络线程模型,并演示了如何利用事件模型。它可以分布在许多节点上。而且速度很快。不是我的代码。

-module(p12dist).  
-author("Jannich Brendle, jannich@bredsaal.dk, http://blog.bredsaal.dk").  
-compile(export_all).

server() ->  
  server(1).

server(Number) ->  
  receive {getwork, Worker_PID} -> Worker_PID ! {work,Number,Number+100},  
  server(Number+101);  
  {result,T} -> io:format("The result is: \~w.\~n", [T]);  
  _ -> server(Number)  
  end.

worker(Server_PID) ->  
  Server_PID ! {getwork, self()},  
  receive {work,Start,End} -> solve(Start,End,Server_PID)  
  end,  
  worker(Server_PID).

start() ->  
  Server_PID = spawn(p12dist, server, []),  
  spawn(p12dist, worker, [Server_PID]),  
  spawn(p12dist, worker, [Server_PID]),  
  spawn(p12dist, worker, [Server_PID]),  
  spawn(p12dist, worker, [Server_PID]).

solve(N,End,_) when N =:= End -> no_solution;

solve(N,End,Server_PID) ->  
  T=round(N*(N+1)/2),
  case (divisor(T,round(math:sqrt(T))) > 500) of  
    true ->  
      Server_PID ! {result,T};  
    false ->  
      solve(N+1,End,Server_PID)  
  end.

divisors(N) ->  
  divisor(N,round(math:sqrt(N))).

divisor(_,0) -> 1;  
divisor(N,I) ->  
  case (N rem I) =:= 0 of  
  true ->  
    2+divisor(N,I-1);  
  false ->  
    divisor(N,I-1)  
  end.

下面的测试发生在Intel(R) Atom(TM) CPU N270 @ 1.60GHz上

~$ time erl -noshell -s p12dist start

The result is: 76576500.

^C

BREAK: (a)bort (c)ontinue (p)roc info (i)nfo (l)oaded
       (v)ersion (k)ill (D)b-tables (d)istribution
a

real    0m5.510s
user    0m5.836s
sys 0m0.152s

使用Haskell,您真的不需要显式地考虑递归。

factorCount number = foldr factorCount' 0 [1..isquare] -
                     (fromEnum $ square == fromIntegral isquare)
    where
      square = sqrt $ fromIntegral number
      isquare = floor square
      factorCount' candidate
        | number `rem` candidate == 0 = (2 +)
        | otherwise = id

triangles :: [Int]
triangles = scanl1 (+) [1,2..]

main = print . head $ dropWhile ((< 1001) . factorCount) triangles

在上面的代码中,我用普通的列表操作替换了@Thomas回答中的显式递归。代码仍然做着完全相同的事情,而不需要我们担心尾部递归。它运行(~ 7.49秒)比@Thomas回答的版本(~ 7.04秒)在我的机器上运行GHC 7.6.2,而来自@Raedwulf的C版本运行~ 3.15秒。GHC似乎在过去一年中有所改善。

PS:我知道这是一个老问题,我从谷歌搜索中偶然发现了它(我忘了我在搜索什么了,现在…)只是想评论一下关于LCO的问题,并表达我对Haskell的总体感受。我想对上面的答案进行注释,但是注释不允许代码块。