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
尝试:
package main
import "fmt"
import "math"
func main() {
var n, m, c int
for i := 1; ; i++ {
n, m, c = i * (i + 1) / 2, int(math.Sqrt(float64(n))), 0
for f := 1; f < m; f++ {
if n % f == 0 { c++ }
}
c *= 2
if m * m == n { c ++ }
if c > 1001 {
fmt.Println(n)
break
}
}
}
我得到:
原始版本:9.1690 100%
Go: 8.2520 111%
但使用:
package main
import (
"math"
"fmt"
)
// Sieve of Eratosthenes
func PrimesBelow(limit int) []int {
switch {
case limit < 2:
return []int{}
case limit == 2:
return []int{2}
}
sievebound := (limit - 1) / 2
sieve := make([]bool, sievebound+1)
crosslimit := int(math.Sqrt(float64(limit))-1) / 2
for i := 1; i <= crosslimit; i++ {
if !sieve[i] {
for j := 2 * i * (i + 1); j <= sievebound; j += 2*i + 1 {
sieve[j] = true
}
}
}
plimit := int(1.3*float64(limit)) / int(math.Log(float64(limit)))
primes := make([]int, plimit)
p := 1
primes[0] = 2
for i := 1; i <= sievebound; i++ {
if !sieve[i] {
primes[p] = 2*i + 1
p++
if p >= plimit {
break
}
}
}
last := len(primes) - 1
for i := last; i > 0; i-- {
if primes[i] != 0 {
break
}
last = i
}
return primes[0:last]
}
func main() {
fmt.Println(p12())
}
// Requires PrimesBelow from utils.go
func p12() int {
n, dn, cnt := 3, 2, 0
primearray := PrimesBelow(1000000)
for cnt <= 1001 {
n++
n1 := n
if n1%2 == 0 {
n1 /= 2
}
dn1 := 1
for i := 0; i < len(primearray); i++ {
if primearray[i]*primearray[i] > n1 {
dn1 *= 2
break
}
exponent := 1
for n1%primearray[i] == 0 {
exponent++
n1 /= primearray[i]
}
if exponent > 1 {
dn1 *= exponent
}
if n1 == 1 {
break
}
}
cnt = dn * dn1
dn = dn1
}
return n * (n - 1) / 2
}
我得到:
原始版本:9.1690 100%
Thaumkid的c版本:0.1060 8650%
首发版本:8.2520 111%
第二围棋版本:0.0230 39865%
我还尝试了Python3.6和pypy3.3-5.5-alpha:
原版本:8.629 100%
Thaumkid的c版本:0.109 7916%
python: 54.795 16%
Pypy3.3-5.5-alpha: 13.291 65%
然后用下面的代码我得到:
原版本:8.629 100%
Thaumkid的c版本:0.109 8650%
Python3.6: 1.489 580%
Pypy3.3-5.5-alpha: 0.582 1483%
def D(N):
if N == 1: return 1
sqrtN = int(N ** 0.5)
nf = 1
for d in range(2, sqrtN + 1):
if N % d == 0:
nf = nf + 1
return 2 * nf - (1 if sqrtN**2 == N else 0)
L = 1000
Dt, n = 0, 0
while Dt <= L:
t = n * (n + 1) // 2
Dt = D(n/2)*D(n+1) if n%2 == 0 else D(n)*D((n+1)/2)
n = n + 1
print (t)
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x86_64 Core2 Duo (2.5GHz)机器上使用GHC 7.0.3, gcc 4.4.6, Linux 2.6.29,对Haskell使用GHC -O2 - flvm - force-recomp编译,对C使用gcc -O3 -lm编译。
Your C routine runs in 8.4 seconds (faster than your run probably because of -O3)
The Haskell solution runs in 36 seconds (due to the -O2 flag)
Your factorCount' code isn't explicitly typed and defaulting to Integer (thanks to Daniel for correcting my misdiagnosis here!). Giving an explicit type signature (which is standard practice anyway) using Int and the time changes to 11.1 seconds
in factorCount' you have needlessly called fromIntegral. A fix results in no change though (the compiler is smart, lucky for you).
You used mod where rem is faster and sufficient. This changes the time to 8.5 seconds.
factorCount' is constantly applying two extra arguments that never change (number, sqrt). A worker/wrapper transformation gives us:
$ time ./so
842161320
real 0m7.954s
user 0m7.944s
sys 0m0.004s
没错,7.95秒。始终比C方案快半秒。没有- flvm标志,我仍然得到8.182秒,所以NCG后端在这种情况下也做得很好。
结论:Haskell非常棒。
生成的代码
factorCount number = factorCount' number isquare 1 0 - (fromEnum $ square == fromIntegral isquare)
where square = sqrt $ fromIntegral number
isquare = floor square
factorCount' :: Int -> Int -> Int -> Int -> Int
factorCount' number sqrt candidate0 count0 = go candidate0 count0
where
go candidate count
| candidate > sqrt = count
| number `rem` candidate == 0 = go (candidate + 1) (count + 2)
| otherwise = go (candidate + 1) count
nextTriangle index triangle
| factorCount triangle > 1000 = triangle
| otherwise = nextTriangle (index + 1) (triangle + index + 1)
main = print $ nextTriangle 1 1
编辑:现在我们已经探讨了这个问题,让我们来解决问题
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 ?
在Haskell中,使用Integer比Int慢,但慢多少取决于执行的计算。幸运的是(对于64位机器)Int就足够了。出于可移植性的考虑,你可能应该重写我的代码,使用Int64或Word64 (C不是唯一的语言长)。
问题2:为什么haskell这么慢?有编译器标志吗
关闭刹车还是我的实现?(后者相当
就像haskell对我来说是一本有七个印章的书一样。)
问题3:你能给我一些建议吗
实现而不改变我确定因子的方式?
以任何方式优化:更好、更快、更“原生”的语言。
这就是我上面所回答的。答案是
0)通过-O2进行优化
1)尽可能使用快速(特别是不可装箱的)类型
2) rem not mod(一个经常被遗忘的优化)和
3)工人/包装器转换(可能是最常见的优化)。
问题4:我的功能实现是否允许LCO,因此
避免添加不必要的帧到调用堆栈?
是的,这不是问题所在。干得好,很高兴你考虑到这一点。
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。