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

如果你使用c++,另一个选择是使用模板元编程:

// recursive template to sum bits in an int
template <int BITS>
int countBits(int val) {
        // return the least significant bit plus the result of calling ourselves with
        // .. the shifted value
        return (val & 0x1) + countBits<BITS-1>(val >> 1);
}

// template specialisation to terminate the recursion when there's only one bit left
template<>
int countBits<1>(int val) {
        return val & 0x1;
}

用法如下:

// to count bits in a byte/char (this returns 8)
countBits<8>( 255 )

// another byte (this returns 7)
countBits<8>( 254 )

// counting bits in a word/short (this returns 1)
countBits<16>( 256 )

当然,你可以进一步扩展这个模板来使用不同的类型(甚至是自动检测位大小),但为了清晰起见,我让它保持简单。

edit:忘了说这很好,因为它应该在任何c++编译器中工作,它基本上只是为你展开循环,如果一个常量值用于比特计数(换句话说,我很确定这是你能找到的最快的通用方法)

其他回答

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。

我个人使用这个:

  public static int myBitCount(long L){
      int count = 0;
      while (L != 0) {
         count++;
         L ^= L & -L; 
      }
      return count;
  }
def hammingWeight(n):
    count = 0
    while n:
        if n&1:
            count += 1
        n >>= 1
    return count

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;
}

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。