代表数字7的8位像这样:

00000111

设置了三个比特。

确定32位整数中设置位数的算法是什么?


当前回答

你可以使用内置函数__builtin_popcount()。c++中没有__builtin_popcount,但它是GCC编译器的内置函数。这个函数返回一个整数中的设置位数。

int __builtin_popcount (unsigned int x);

参考:Bit Twiddling Hacks

其他回答

这里有一个到目前为止还没有提到的解决方案,使用位字段。下面的程序使用4种不同的方法对100000000个16位整数数组中的设置位进行计数。计时结果在括号中给出(在MacOSX上,使用gcc -O3):

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

#define LENGTH 100000000

typedef struct {
    unsigned char bit0 : 1;
    unsigned char bit1 : 1;
    unsigned char bit2 : 1;
    unsigned char bit3 : 1;
    unsigned char bit4 : 1;
    unsigned char bit5 : 1;
    unsigned char bit6 : 1;
    unsigned char bit7 : 1;
} bits;

unsigned char sum_bits(const unsigned char x) {
    const bits *b = (const bits*) &x;
    return b->bit0 + b->bit1 + b->bit2 + b->bit3 \
         + b->bit4 + b->bit5 + b->bit6 + b->bit7;
}

int NumberOfSetBits(int i) {
    i = i - ((i >> 1) & 0x55555555);
    i = (i & 0x33333333) + ((i >> 2) & 0x33333333);
    return (((i + (i >> 4)) & 0x0F0F0F0F) * 0x01010101) >> 24;
}

#define out(s) \
    printf("bits set: %lu\nbits counted: %lu\n", 8*LENGTH*sizeof(short)*3/4, s);

int main(int argc, char **argv) {
    unsigned long i, s;
    unsigned short *x = malloc(LENGTH*sizeof(short));
    unsigned char lut[65536], *p;
    unsigned short *ps;
    int *pi;

    /* set 3/4 of the bits */
    for (i=0; i<LENGTH; ++i)
        x[i] = 0xFFF0;

    /* sum_bits (1.772s) */
    for (i=LENGTH*sizeof(short), p=(unsigned char*) x, s=0; i--; s+=sum_bits(*p++));
    out(s);

    /* NumberOfSetBits (0.404s) */
    for (i=LENGTH*sizeof(short)/sizeof(int), pi=(int*)x, s=0; i--; s+=NumberOfSetBits(*pi++));
    out(s);

    /* populate lookup table */
    for (i=0, p=(unsigned char*) &i; i<sizeof(lut); ++i)
        lut[i] = sum_bits(p[0]) + sum_bits(p[1]);

    /* 256-bytes lookup table (0.317s) */
    for (i=LENGTH*sizeof(short), p=(unsigned char*) x, s=0; i--; s+=lut[*p++]);
    out(s);

    /* 65536-bytes lookup table (0.250s) */
    for (i=LENGTH, ps=x, s=0; i--; s+=lut[*ps++]);
    out(s);

    free(x);
    return 0;
}

虽然位域版本非常可读,但计时结果显示它比NumberOfSetBits()慢了4倍以上。基于查找表的实现仍然要快得多,特别是对于一个65 kB的表。

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;
}

一个快速的c#解决方案,使用预先计算的字节位计数表,并根据输入大小进行分支。

public static class BitCount
{
    public static uint GetSetBitsCount(uint n)
    {
        var counts = BYTE_BIT_COUNTS;
        return n <= 0xff ? counts[n]
             : n <= 0xffff ? counts[n & 0xff] + counts[n >> 8]
             : n <= 0xffffff ? counts[n & 0xff] + counts[(n >> 8) & 0xff] + counts[(n >> 16) & 0xff]
             : counts[n & 0xff] + counts[(n >> 8) & 0xff] + counts[(n >> 16) & 0xff] + counts[(n >> 24) & 0xff];
    }

    public static readonly uint[] BYTE_BIT_COUNTS =
    {
        0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
        1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
        1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
        1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
        2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
        3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
        3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
        4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
    };
}

这也可以正常工作:

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

当你写出比特模式时,“黑客的喜悦”比特旋转变得更加清晰。

unsigned int bitCount(unsigned int x)
{
  x = ((x >> 1) & 0b01010101010101010101010101010101)
     + (x       & 0b01010101010101010101010101010101);
  x = ((x >> 2) & 0b00110011001100110011001100110011)
     + (x       & 0b00110011001100110011001100110011); 
  x = ((x >> 4) & 0b00001111000011110000111100001111)
     + (x       & 0b00001111000011110000111100001111); 
  x = ((x >> 8) & 0b00000000111111110000000011111111)
     + (x       & 0b00000000111111110000000011111111); 
  x = ((x >> 16)& 0b00000000000000001111111111111111)
     + (x       & 0b00000000000000001111111111111111); 
  return x;
}

第一步将偶数位加到奇数位上,产生每两个位的和。其他步骤将高阶数据块添加到低阶数据块,将数据块的大小一直增加一倍,直到最终计数占用整个int。