这也可以正常工作:

int ans = 0;
while(num) {
  ans += (num & 1);
  num = num >> 1;
}    
return ans;

unsigned int count_bit(unsigned int x)
{
  x = (x & 0x55555555) + ((x >> 1) & 0x55555555);
  x = (x & 0x33333333) + ((x >> 2) & 0x33333333);
  x = (x & 0x0F0F0F0F) + ((x >> 4) & 0x0F0F0F0F);
  x = (x & 0x00FF00FF) + ((x >> 8) & 0x00FF00FF);
  x = (x & 0x0000FFFF) + ((x >> 16)& 0x0000FFFF);
  return x;
}

我来解释一下这个算法。

该算法基于分治算法。假设有一个8位整数213(二进制的11010101)，算法是这样工作的(每次合并两个邻居块):

+-------------------------------+
| 1 | 1 | 0 | 1 | 0 | 1 | 0 | 1 |  <- x
|  1 0  |  0 1  |  0 1  |  0 1  |  <- first time merge
|    0 0 1 1    |    0 0 1 0    |  <- second time merge
|        0 0 0 0 0 1 0 1        |  <- third time ( answer = 00000101 = 5)
+-------------------------------+

public class BinaryCounter {

private int N;

public BinaryCounter(int N) {
    this.N = N;
}

public static void main(String[] args) {

    BinaryCounter counter=new BinaryCounter(7);     
    System.out.println("Number of ones is "+ counter.count());

}

public int count(){
    if(N<=0) return 0;
    int counter=0;
    int K = 0;
    do{
        K = biggestPowerOfTwoSmallerThan(N);
        N = N-K;
        counter++;
    }while (N != 0);
    return counter;

}

private int biggestPowerOfTwoSmallerThan(int N) {
    if(N==1) return 1;
    for(int i=0;i<N;i++){
        if(Math.pow(2, i) > N){
            int power = i-1;
            return (int) Math.pow(2, power);
        }
    }
    return 0;
}
}

天真的解决方案

时间复杂度为O(no。n的比特数)

int countSet(unsigned int n)
{
    int res=0;
    while(n!=0){
      res += (n&1);
      n >>= 1;      // logical right shift, like C unsigned or Java >>>
    }
   return res;
}

Brian Kerningam的算法

时间复杂度为O(n中设置位的个数)

int countSet(unsigned int n)
{
  int res=0;
  while(n != 0)
  {
    n = (n & (n-1));
    res++;
  }
  return res;
} 

32位数字的查找表方法-在这种方法中，我们将32位数字分解为4个8位数字的块

时间复杂度为O(1)

static unsigned char table[256]; /* the table size is 256,
                        the number of values i&0xFF (8 bits) can have */

void initialize() //holds the number of set bits from 0 to 255
{
  table[0]=0;
  for(unsigned int i=1;i<256;i++)
     table[i]=(i&1)+table[i>>1];
}

int countSet(unsigned int n)
{
  // 0xff is hexadecimal representation of 8 set bits.
  int res=table[n & 0xff];
  n=n>>8;
  res=res+ table[n & 0xff];
  n=n>>8;
  res=res+ table[n & 0xff];
  n=n>>8;
  res=res+ table[n & 0xff];
  return res;
}

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

我发现了一个在数组中使用SIMD指令(SSSE3和AVX2)的位计数实现。它的性能比使用__popcnt64内禀函数要好2-2.5倍。

SSSE3版:

#include <smmintrin.h>
#include <stdint.h>

const __m128i Z = _mm_set1_epi8(0x0);
const __m128i F = _mm_set1_epi8(0xF);
//Vector with pre-calculated bit count:
const __m128i T = _mm_setr_epi8(0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4);

uint64_t BitCount(const uint8_t * src, size_t size)
{
    __m128i _sum =  _mm128_setzero_si128();
    for (size_t i = 0; i < size; i += 16)
    {
        //load 16-byte vector
        __m128i _src = _mm_loadu_si128((__m128i*)(src + i));
        //get low 4 bit for every byte in vector
        __m128i lo = _mm_and_si128(_src, F);
        //sum precalculated value from T
        _sum = _mm_add_epi64(_sum, _mm_sad_epu8(Z, _mm_shuffle_epi8(T, lo)));
        //get high 4 bit for every byte in vector
        __m128i hi = _mm_and_si128(_mm_srli_epi16(_src, 4), F);
        //sum precalculated value from T
        _sum = _mm_add_epi64(_sum, _mm_sad_epu8(Z, _mm_shuffle_epi8(T, hi)));
    }
    uint64_t sum[2];
    _mm_storeu_si128((__m128i*)sum, _sum);
    return sum[0] + sum[1];
}

AVX2 版本：

#include <immintrin.h>
#include <stdint.h>

const __m256i Z = _mm256_set1_epi8(0x0);
const __m256i F = _mm256_set1_epi8(0xF);
//Vector with pre-calculated bit count:
const __m256i T = _mm256_setr_epi8(0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4, 
                                   0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4);

uint64_t BitCount(const uint8_t * src, size_t size)
{
    __m256i _sum =  _mm256_setzero_si256();
    for (size_t i = 0; i < size; i += 32)
    {
        //load 32-byte vector
        __m256i _src = _mm256_loadu_si256((__m256i*)(src + i));
        //get low 4 bit for every byte in vector
        __m256i lo = _mm256_and_si256(_src, F);
        //sum precalculated value from T
        _sum = _mm256_add_epi64(_sum, _mm256_sad_epu8(Z, _mm256_shuffle_epi8(T, lo)));
        //get high 4 bit for every byte in vector
        __m256i hi = _mm256_and_si256(_mm256_srli_epi16(_src, 4), F);
        //sum precalculated value from T
        _sum = _mm256_add_epi64(_sum, _mm256_sad_epu8(Z, _mm256_shuffle_epi8(T, hi)));
    }
    uint64_t sum[4];
    _mm256_storeu_si256((__m256i*)sum, _sum);
    return sum[0] + sum[1] + sum[2] + sum[3];
}