我正在寻找最快的方法来获得π的值,作为一个个人挑战。更具体地说,我使用的方法不涉及使用#define常量M_PI,或硬编码的数字。

下面的程序测试了我所知道的各种方法。从理论上讲,内联汇编版本是最快的选择,尽管显然不能移植。我将它作为一个基准,与其他版本进行比较。在我的测试中,使用内置函数,4 * atan(1)版本在GCC 4.2上是最快的,因为它自动将atan(1)折叠成一个常量。通过指定-fno-builtin, atan2(0, -1)版本是最快的。

下面是主要的测试程序(pitimes.c):

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

#define ITERS 10000000
#define TESTWITH(x) {                                                       \
    diff = 0.0;                                                             \
    time1 = clock();                                                        \
    for (i = 0; i < ITERS; ++i)                                             \
        diff += (x) - M_PI;                                                 \
    time2 = clock();                                                        \
    printf("%s\t=> %e, time => %f\n", #x, diff, diffclock(time2, time1));   \
}

static inline double
diffclock(clock_t time1, clock_t time0)
{
    return (double) (time1 - time0) / CLOCKS_PER_SEC;
}

int
main()
{
    int i;
    clock_t time1, time2;
    double diff;

    /* Warmup. The atan2 case catches GCC's atan folding (which would
     * optimise the ``4 * atan(1) - M_PI'' to a no-op), if -fno-builtin
     * is not used. */
    TESTWITH(4 * atan(1))
    TESTWITH(4 * atan2(1, 1))

#if defined(__GNUC__) && (defined(__i386__) || defined(__amd64__))
    extern double fldpi();
    TESTWITH(fldpi())
#endif

    /* Actual tests start here. */
    TESTWITH(atan2(0, -1))
    TESTWITH(acos(-1))
    TESTWITH(2 * asin(1))
    TESTWITH(4 * atan2(1, 1))
    TESTWITH(4 * atan(1))

    return 0;
}

内联汇编的东西(fldpi.c)只适用于x86和x64系统:

double
fldpi()
{
    double pi;
    asm("fldpi" : "=t" (pi));
    return pi;
}

和一个构建脚本,构建我正在测试的所有配置(build.sh):

#!/bin/sh
gcc -O3 -Wall -c           -m32 -o fldpi-32.o fldpi.c
gcc -O3 -Wall -c           -m64 -o fldpi-64.o fldpi.c

gcc -O3 -Wall -ffast-math  -m32 -o pitimes1-32 pitimes.c fldpi-32.o
gcc -O3 -Wall              -m32 -o pitimes2-32 pitimes.c fldpi-32.o -lm
gcc -O3 -Wall -fno-builtin -m32 -o pitimes3-32 pitimes.c fldpi-32.o -lm
gcc -O3 -Wall -ffast-math  -m64 -o pitimes1-64 pitimes.c fldpi-64.o -lm
gcc -O3 -Wall              -m64 -o pitimes2-64 pitimes.c fldpi-64.o -lm
gcc -O3 -Wall -fno-builtin -m64 -o pitimes3-64 pitimes.c fldpi-64.o -lm

除了在各种编译器标志之间进行测试(我也比较了32位和64位,因为优化是不同的),我还尝试切换测试的顺序。但是,atan2(0, -1)版本在每次测试中仍然名列前茅。


当前回答

在编译时用D计算PI。

(摘自DSource.org)

/** Calculate pi at compile time
 *
 * Compile with dmd -c pi.d
 */
module calcpi;

import meta.math;
import meta.conv;

/** real evaluateSeries!(real x, real metafunction!(real y, int n) term)
 *
 * Evaluate a power series at compile time.
 *
 * Given a metafunction of the form
 *  real term!(real y, int n),
 * which gives the nth term of a convergent series at the point y
 * (where the first term is n==1), and a real number x,
 * this metafunction calculates the infinite sum at the point x
 * by adding terms until the sum doesn't change any more.
 */
template evaluateSeries(real x, alias term, int n=1, real sumsofar=0.0)
{
  static if (n>1 && sumsofar == sumsofar + term!(x, n+1)) {
     const real evaluateSeries = sumsofar;
  } else {
     const real evaluateSeries = evaluateSeries!(x, term, n+1, sumsofar + term!(x, n));
  }
}

/*** Calculate atan(x) at compile time.
 *
 * Uses the Maclaurin formula
 *  atan(z) = z - z^3/3 + Z^5/5 - Z^7/7 + ...
 */
template atan(real z)
{
    const real atan = evaluateSeries!(z, atanTerm);
}

template atanTerm(real x, int n)
{
    const real atanTerm =  (n & 1 ? 1 : -1) * pow!(x, 2*n-1)/(2*n-1);
}

/// Machin's formula for pi
/// pi/4 = 4 atan(1/5) - atan(1/239).
pragma(msg, "PI = " ~ fcvt!(4.0 * (4*atan!(1/5.0) - atan!(1/239.0))) );

其他回答

为了完整起见,一个c++模板版本,对于一个优化的构建,它将在编译时计算PI的近似值,并将内联到单个值。

#include <iostream>

template<int I>
struct sign
{
    enum {value = (I % 2) == 0 ? 1 : -1};
};

template<int I, int J>
struct pi_calc
{
    inline static double value ()
    {
        return (pi_calc<I-1, J>::value () + pi_calc<I-1, J+1>::value ()) / 2.0;
    }
};

template<int J>
struct pi_calc<0, J>
{
    inline static double value ()
    {
        return (sign<J>::value * 4.0) / (2.0 * J + 1.0) + pi_calc<0, J-1>::value ();
    }
};


template<>
struct pi_calc<0, 0>
{
    inline static double value ()
    {
        return 4.0;
    }
};

template<int I>
struct pi
{
    inline static double value ()
    {
        return pi_calc<I, I>::value ();
    }
};

int main ()
{
    std::cout.precision (12);

    const double pi_value = pi<10>::value ();

    std::cout << "pi ~ " << pi_value << std::endl;

    return 0;
}

注意,对于I > 10,优化构建可能会很慢,对于非优化运行也是如此。对于12次迭代,我相信大约有80k次调用value()(在没有内存的情况下)。

Chudnovsky算法非常快如果你不介意做一个平方根和几个逆运算的话。它在2次迭代中收敛到两倍精度。

/*
    Chudnovsky algorithm for computing PI
*/

#include <iostream>
#include <cmath>
using namespace std;

double calc_PI(int K=2) {

    static const int A = 545140134;
    static const int B = 13591409;
    static const int D = 640320;

    const double ID3 = 1./ (double(D)*double(D)*double(D));

    double sum = 0.;
    double b   = sqrt(ID3);
    long long int p = 1;
    long long int a = B;

    sum += double(p) * double(a)* b;

    // 2 iterations enough for double convergence
    for (int k=1; k<K; ++k) {
        // A*k + B
        a += A;
        // update denominator
        b *= ID3;
        // p = (-1)^k 6k! / 3k! k!^3
        p *= (6*k)*(6*k-1)*(6*k-2)*(6*k-3)*(6*k-4)*(6*k-5);
        p /= (3*k)*(3*k-1)*(3*k-2) * k*k*k;
        p = -p;

        sum += double(p) * double(a)* b;
    }

    return 1./(12*sum);
}

int main() {

    cout.precision(16);
    cout.setf(ios::fixed);

    for (int k=1; k<=5; ++k) cout << "k = " << k << "   PI = " << calc_PI(k) << endl;

    return 0;
}

结果:

k = 1   PI = 3.1415926535897341
k = 2   PI = 3.1415926535897931
k = 3   PI = 3.1415926535897931
k = 4   PI = 3.1415926535897931
k = 5   PI = 3.1415926535897931

我认为圆周率的值是圆的周长和半径之比。

它可以通过常规的数学计算简单地实现

正好是3![弗林克教授(辛普森一家)]

开玩笑,但这里有一个在c#(。微软网络框架。

using System;
using System.Text;

class Program {
    static void Main(string[] args) {
        int Digits = 100;

        BigNumber x = new BigNumber(Digits);
        BigNumber y = new BigNumber(Digits);
        x.ArcTan(16, 5);
        y.ArcTan(4, 239);
        x.Subtract(y);
        string pi = x.ToString();
        Console.WriteLine(pi);
    }
}

public class BigNumber {
    private UInt32[] number;
    private int size;
    private int maxDigits;

    public BigNumber(int maxDigits) {
        this.maxDigits = maxDigits;
        this.size = (int)Math.Ceiling((float)maxDigits * 0.104) + 2;
        number = new UInt32[size];
    }
    public BigNumber(int maxDigits, UInt32 intPart)
        : this(maxDigits) {
        number[0] = intPart;
        for (int i = 1; i < size; i++) {
            number[i] = 0;
        }
    }
    private void VerifySameSize(BigNumber value) {
        if (Object.ReferenceEquals(this, value))
            throw new Exception("BigNumbers cannot operate on themselves");
        if (value.size != this.size)
            throw new Exception("BigNumbers must have the same size");
    }

    public void Add(BigNumber value) {
        VerifySameSize(value);

        int index = size - 1;
        while (index >= 0 && value.number[index] == 0)
            index--;

        UInt32 carry = 0;
        while (index >= 0) {
            UInt64 result = (UInt64)number[index] +
                            value.number[index] + carry;
            number[index] = (UInt32)result;
            if (result >= 0x100000000U)
                carry = 1;
            else
                carry = 0;
            index--;
        }
    }
    public void Subtract(BigNumber value) {
        VerifySameSize(value);

        int index = size - 1;
        while (index >= 0 && value.number[index] == 0)
            index--;

        UInt32 borrow = 0;
        while (index >= 0) {
            UInt64 result = 0x100000000U + (UInt64)number[index] -
                            value.number[index] - borrow;
            number[index] = (UInt32)result;
            if (result >= 0x100000000U)
                borrow = 0;
            else
                borrow = 1;
            index--;
        }
    }
    public void Multiply(UInt32 value) {
        int index = size - 1;
        while (index >= 0 && number[index] == 0)
            index--;

        UInt32 carry = 0;
        while (index >= 0) {
            UInt64 result = (UInt64)number[index] * value + carry;
            number[index] = (UInt32)result;
            carry = (UInt32)(result >> 32);
            index--;
        }
    }
    public void Divide(UInt32 value) {
        int index = 0;
        while (index < size && number[index] == 0)
            index++;

        UInt32 carry = 0;
        while (index < size) {
            UInt64 result = number[index] + ((UInt64)carry << 32);
            number[index] = (UInt32)(result / (UInt64)value);
            carry = (UInt32)(result % (UInt64)value);
            index++;
        }
    }
    public void Assign(BigNumber value) {
        VerifySameSize(value);
        for (int i = 0; i < size; i++) {
            number[i] = value.number[i];
        }
    }

    public override string ToString() {
        BigNumber temp = new BigNumber(maxDigits);
        temp.Assign(this);

        StringBuilder sb = new StringBuilder();
        sb.Append(temp.number[0]);
        sb.Append(System.Globalization.CultureInfo.CurrentCulture.NumberFormat.CurrencyDecimalSeparator);

        int digitCount = 0;
        while (digitCount < maxDigits) {
            temp.number[0] = 0;
            temp.Multiply(100000);
            sb.AppendFormat("{0:D5}", temp.number[0]);
            digitCount += 5;
        }

        return sb.ToString();
    }
    public bool IsZero() {
        foreach (UInt32 item in number) {
            if (item != 0)
                return false;
        }
        return true;
    }

    public void ArcTan(UInt32 multiplicand, UInt32 reciprocal) {
        BigNumber X = new BigNumber(maxDigits, multiplicand);
        X.Divide(reciprocal);
        reciprocal *= reciprocal;

        this.Assign(X);

        BigNumber term = new BigNumber(maxDigits);
        UInt32 divisor = 1;
        bool subtractTerm = true;
        while (true) {
            X.Divide(reciprocal);
            term.Assign(X);
            divisor += 2;
            term.Divide(divisor);
            if (term.IsZero())
                break;

            if (subtractTerm)
                this.Subtract(term);
            else
                this.Add(term);
            subtractTerm = !subtractTerm;
        }
    }
}

这个版本(在Delphi中)没有什么特别的,但它至少比Nick Hodge在他的博客上发布的版本快:)。在我的机器上,执行十亿次迭代大约需要16秒,得到的值为3.1415926525879(准确的部分用粗体显示)。

program calcpi;

{$APPTYPE CONSOLE}

uses
  SysUtils;

var
  start, finish: TDateTime;

function CalculatePi(iterations: integer): double;
var
  numerator, denominator, i: integer;
  sum: double;
begin
  {
  PI may be approximated with this formula:
  4 * (1 - 1/3 + 1/5 - 1/7 + 1/9 - 1/11 .......)
  //}
  numerator := 1;
  denominator := 1;
  sum := 0;
  for i := 1 to iterations do begin
    sum := sum + (numerator/denominator);
    denominator := denominator + 2;
    numerator := -numerator;
  end;
  Result := 4 * sum;
end;

begin
  try
    start := Now;
    WriteLn(FloatToStr(CalculatePi(StrToInt(ParamStr(1)))));
    finish := Now;
    WriteLn('Seconds:' + FormatDateTime('hh:mm:ss.zz',finish-start));
  except
    on E:Exception do
      Writeln(E.Classname, ': ', E.Message);
  end;
end.