摘自《黑客的喜悦》第66页，图5-2

int pop(unsigned x)
{
    x = x - ((x >> 1) & 0x55555555);
    x = (x & 0x33333333) + ((x >> 2) & 0x33333333);
    x = (x + (x >> 4)) & 0x0F0F0F0F;
    x = x + (x >> 8);
    x = x + (x >> 16);
    return x & 0x0000003F;
}

执行大约20条指令(依赖于arch)，没有分支。黑客的喜悦是令人愉快的!强烈推荐。

这是一个可移植的模块(ANSI-C)，它可以在任何架构上对每个算法进行基准测试。

你的CPU有9位字节?目前它实现了2个算法，K&R算法和一个字节查找表。查找表的平均速度比K&R算法快3倍。如果有人能想出办法使“黑客的喜悦”算法可移植，请随意添加它。

#ifndef _BITCOUNT_H_
#define _BITCOUNT_H_

/* Return the Hamming Wieght of val, i.e. the number of 'on' bits. */
int bitcount( unsigned int );

/* List of available bitcount algorithms.  
 * onTheFly:    Calculate the bitcount on demand.
 *
 * lookupTalbe: Uses a small lookup table to determine the bitcount.  This
 * method is on average 3 times as fast as onTheFly, but incurs a small
 * upfront cost to initialize the lookup table on the first call.
 *
 * strategyCount is just a placeholder. 
 */
enum strategy { onTheFly, lookupTable, strategyCount };

/* String represenations of the algorithm names */
extern const char *strategyNames[];

/* Choose which bitcount algorithm to use. */
void setStrategy( enum strategy );

#endif

.

#include <limits.h>

#include "bitcount.h"

/* The number of entries needed in the table is equal to the number of unique
 * values a char can represent which is always UCHAR_MAX + 1*/
static unsigned char _bitCountTable[UCHAR_MAX + 1];
static unsigned int _lookupTableInitialized = 0;

static int _defaultBitCount( unsigned int val ) {
    int count;

    /* Starting with:
     * 1100 - 1 == 1011,  1100 & 1011 == 1000
     * 1000 - 1 == 0111,  1000 & 0111 == 0000
     */
    for ( count = 0; val; ++count )
        val &= val - 1;

    return count;
}

/* Looks up each byte of the integer in a lookup table.
 *
 * The first time the function is called it initializes the lookup table.
 */
static int _tableBitCount( unsigned int val ) {
    int bCount = 0;

    if ( !_lookupTableInitialized ) {
        unsigned int i;
        for ( i = 0; i != UCHAR_MAX + 1; ++i )
            _bitCountTable[i] =
                ( unsigned char )_defaultBitCount( i );

        _lookupTableInitialized = 1;
    }

    for ( ; val; val >>= CHAR_BIT )
        bCount += _bitCountTable[val & UCHAR_MAX];

    return bCount;
}

static int ( *_bitcount ) ( unsigned int ) = _defaultBitCount;

const char *strategyNames[] = { "onTheFly", "lookupTable" };

void setStrategy( enum strategy s ) {
    switch ( s ) {
    case onTheFly:
        _bitcount = _defaultBitCount;
        break;
    case lookupTable:
        _bitcount = _tableBitCount;
        break;
    case strategyCount:
        break;
    }
}

/* Just a forwarding function which will call whichever version of the
 * algorithm has been selected by the client 
 */
int bitcount( unsigned int val ) {
    return _bitcount( val );
}

#ifdef _BITCOUNT_EXE_

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

/* Use the same sequence of pseudo random numbers to benmark each Hamming
 * Weight algorithm.
 */
void benchmark( int reps ) {
    clock_t start, stop;
    int i, j;
    static const int iterations = 1000000;

    for ( j = 0; j != strategyCount; ++j ) {
        setStrategy( j );

        srand( 257 );

        start = clock(  );

        for ( i = 0; i != reps * iterations; ++i )
            bitcount( rand(  ) );

        stop = clock(  );

        printf
            ( "\n\t%d psudoe-random integers using %s: %f seconds\n\n",
              reps * iterations, strategyNames[j],
              ( double )( stop - start ) / CLOCKS_PER_SEC );
    }
}

int main( void ) {
    int option;

    while ( 1 ) {
        printf( "Menu Options\n"
            "\t1.\tPrint the Hamming Weight of an Integer\n"
            "\t2.\tBenchmark Hamming Weight implementations\n"
            "\t3.\tExit ( or cntl-d )\n\n\t" );

        if ( scanf( "%d", &option ) == EOF )
            break;

        switch ( option ) {
        case 1:
            printf( "Please enter the integer: " );
            if ( scanf( "%d", &option ) != EOF )
                printf
                    ( "The Hamming Weight of %d ( 0x%X ) is %d\n\n",
                      option, option, bitcount( option ) );
            break;
        case 2:
            printf
                ( "Please select number of reps ( in millions ): " );
            if ( scanf( "%d", &option ) != EOF )
                benchmark( option );
            break;
        case 3:
            goto EXIT;
            break;
        default:
            printf( "Invalid option\n" );
        }

    }

 EXIT:
    printf( "\n" );

    return 0;
}

#endif

你可以这样做:

int countSetBits(int n)
{
    n=((n&0xAAAAAAAA)>>1) + (n&0x55555555);
    n=((n&0xCCCCCCCC)>>2) + (n&0x33333333);
    n=((n&0xF0F0F0F0)>>4) + (n&0x0F0F0F0F);
    n=((n&0xFF00FF00)>>8) + (n&0x00FF00FF);
    return n;
}

int main()
{
    int n=10;
    printf("Number of set bits: %d",countSetBits(n));
     return 0;
}

海王： http://ideone.com/JhwcX

工作原理如下:

首先，所有的偶数位都向右移动，并与奇数位相加，以计算两组位的数量。 然后我们两人一组，然后四个人，以此类推。

有些语言以一种可以使用有效硬件支持(如果可用的话)的方式可移植地公开操作，而有些语言则希望使用一些不错的库。

例如(从语言表中):

c++有std::bitset<>::count()或c++ 20 std::popcount(T x) Java有Java .lang. integer . bitcount()(也用于Long或BigInteger) c#有system . numbers . bitoperations . popcount () Python有int.bit_count()(从3.10开始)

不过，并不是所有的编译器/库都能在HW支持可用时使用它。(值得注意的是MSVC，即使有选项使std::popcount内联为x86 popcnt，它的std::bitset::count仍然总是使用查找表。这有望在未来的版本中改变。)

当可移植语言没有这种基本的位操作时，还要考虑编译器的内置函数。以GNU C为例:

int __builtin_popcount (unsigned int x);
int __builtin_popcountll (unsigned long long x);

In the worst case (no single-instruction HW support) the compiler will generate a call to a function (which in current GCC uses a shift/and bit-hack like this answer, at least for x86). In the best case the compiler will emit a cpu instruction to do the job. (Just like a * or / operator - GCC will use a hardware multiply or divide instruction if available, otherwise will call a libgcc helper function.) Or even better, if the operand is a compile-time constant after inlining, it can do constant-propagation to get a compile-time-constant popcount result.

GCC内置甚至可以跨多个平台工作。Popcount几乎已经成为x86架构的主流，所以现在开始使用内置是有意义的，这样你就可以重新编译，让它内联硬件指令时，你编译-mpopcnt或包括(例如https://godbolt.org/z/Ma5e5a)。其他架构已经有popcount很多年了，但在x86领域，仍然有一些古老的Core 2和类似的老式AMD cpu在使用。

---

在x86上，你可以告诉编译器它可以通过-mpopcnt(也可以通过-msse4.2暗示)假设支持popcnt指令。参见GCC x86选项。-march=nehalem -mtune=skylake(或-march=任何您希望您的代码假设和调优的CPU)可能是一个不错的选择。在较旧的CPU上运行生成的二进制文件将导致非法指令错误。

要为构建它们的机器优化二进制文件，请使用-march=native(与gcc、clang或ICC一起使用)。

MSVC为x86的popcnt指令提供了一个内在的特性，但与gcc不同的是，它实际上是硬件指令的一个内在特性，需要硬件支持。

---

使用std::bitset<>::count()代替内置的

理论上，任何知道如何有效地为目标CPU进行popcount的编译器都应该通过ISO c++ std::bitset<>来公开该功能。实际上，对于某些目标cpu，在某些情况下使用bit-hack AND/shift/ADD可能会更好。

For target architectures where hardware popcount is an optional extension (like x86), not all compilers have a std::bitset that takes advantage of it when available. For example, MSVC has no way to enable popcnt support at compile time, and it's std::bitset<>::count always uses a table lookup, even with /Ox /arch:AVX (which implies SSE4.2, which in turn implies the popcnt feature.) (Update: see below; that does get MSVC's C++20 std::popcount to use x86 popcnt, but still not its bitset<>::count. MSVC could fix that by updating their standard library headers to use std::popcount when available.)

但是，至少您得到了可以在任何地方工作的可移植的东西，并且使用带有正确目标选项的gcc/clang，您可以获得支持它的体系结构的硬件popcount。

#include <bitset>
#include <limits>
#include <type_traits>

template<typename T>
//static inline  // static if you want to compile with -mpopcnt in one compilation unit but not others
typename std::enable_if<std::is_integral<T>::value,  unsigned >::type 
popcount(T x)
{
    static_assert(std::numeric_limits<T>::radix == 2, "non-binary type");

    // sizeof(x)*CHAR_BIT
    constexpr int bitwidth = std::numeric_limits<T>::digits + std::numeric_limits<T>::is_signed;
    // std::bitset constructor was only unsigned long before C++11.  Beware if porting to C++03
    static_assert(bitwidth <= std::numeric_limits<unsigned long long>::digits, "arg too wide for std::bitset() constructor");

    typedef typename std::make_unsigned<T>::type UT;        // probably not needed, bitset width chops after sign-extension

    std::bitset<bitwidth> bs( static_cast<UT>(x) );
    return bs.count();
}

参见Godbolt编译器资源管理器上gcc、clang、icc和MSVC中的asm。

x86-64 gcc -O3 -std=gnu++11 -mpopcnt输出:

unsigned test_short(short a) { return popcount(a); }
    movzx   eax, di      # note zero-extension, not sign-extension
    popcnt  rax, rax
    ret

unsigned test_int(int a) { return popcount(a); }
    mov     eax, edi
    popcnt  rax, rax        # unnecessary 64-bit operand size
    ret

unsigned test_u64(unsigned long long a) { return popcount(a); }
    xor     eax, eax     # gcc avoids false dependencies for Intel CPUs
    popcnt  rax, rdi
    ret

PowerPC64 gcc -O3 -std=gnu++11发出(对于int arg版本):

    rldicl 3,3,0,32     # zero-extend from 32 to 64-bit
    popcntd 3,3         # popcount
    blr

这个源代码不是x86特定的，也不是gnu特定的，只是在gcc/clang/icc下编译得很好，至少在针对x86(包括x86-64)时是这样。

还要注意，对于没有单指令popcount的体系结构，gcc的回退是逐字节表查找。例如，这对ARM来说就不是什么好事。

c++ 20有std::popcount(T)

不幸的是，当前libstdc++头文件用特殊情况定义了它，if(x==0) return 0;在开始时，clang在编译x86时不会优化:

#include <bit>
int bar(unsigned x) {
    return std::popcount(x);
}

clang 11.0.1 -O3 -std=gnu++20 -march=nehalem （https://godbolt.org/z/arMe5a）

# clang 11
    bar(unsigned int):                                # @bar(unsigned int)
        popcnt  eax, edi
        cmove   eax, edi         # redundant: if popcnt result is 0, return the original 0 instead of the popcnt-generated 0...
        ret

但是GCC编译得很好:

# gcc 10
        xor     eax, eax         # break false dependency on Intel SnB-family before Ice Lake.
        popcnt  eax, edi
        ret

即使是MSVC也能很好地使用它，只要你使用-arch:AVX或更高版本(并使用-std:c++latest启用c++ 20)。https://godbolt.org/z/7K4Gef

int bar(unsigned int) PROC                                 ; bar, COMDAT
        popcnt  eax, ecx
        ret     0
int bar(unsigned int) ENDP                                 ; bar

下面是PHP中的一些东西(所有PHP整数都是32位符号，因此是31位):

function bits_population($nInteger)
{

    $nPop=0;
    while($nInteger)
    {
        $nInteger^=(1<<(floor(1+log($nInteger)/log(2))-1));
        $nPop++;
    }
    return $nPop;
}

"最佳算法"是什么意思?短码还是长码?您的代码看起来非常优雅，并且具有恒定的执行时间。代码也很短。

但如果速度是主要因素，而不是代码大小，那么我认为以下方法可以更快:

       static final int[] BIT_COUNT = { 0, 1, 1, ... 256 values with a bitsize of a byte ... };
        static int bitCountOfByte( int value ){
            return BIT_COUNT[ value & 0xFF ];
        }

        static int bitCountOfInt( int value ){
            return bitCountOfByte( value ) 
                 + bitCountOfByte( value >> 8 ) 
                 + bitCountOfByte( value >> 16 ) 
                 + bitCountOfByte( value >> 24 );
        }

我认为这不会更快的64位值，但32位值可以更快。