#!/user/local/bin/perl


    $c=0x11BBBBAB;
     $count=0;
     $m=0x00000001;
    for($i=0;$i<32;$i++)
    {
        $f=$c & $m;
        if($f == 1)
        {
            $count++;
        }
        $c=$c >> 1;
    }
    printf("%d",$count);

ive done it through a perl script. the number taken is $c=0x11BBBBAB   
B=3 1s   
A=2 1s   
so in total  
1+1+3+3+3+2+3+3=19

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;
  }

Java JDK1.5

Integer.bitCount (n);

其中n是要计算1的数。

检查,

Integer.highestOneBit(n);
Integer.lowestOneBit(n);
Integer.numberOfLeadingZeros(n);
Integer.numberOfTrailingZeros(n);

//Beginning with the value 1, rotate left 16 times
     n = 1;
         for (int i = 0; i < 16; i++) {
            n = Integer.rotateLeft(n, 1);
            System.out.println(n);
         }

为什么不迭代地除以2呢?

count = 0
while n > 0
  if (n % 2) == 1
    count += 1
  n /= 2  

我同意这不是最快的，但是“最好”这个词有点含糊不清。我认为“最好”应该有一个清晰的元素

对于232查找表和逐个遍历每个位之间的折中方法:

int bitcount(unsigned int num){
    int count = 0;
    static int nibblebits[] =
        {0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4};
    for(; num != 0; num >>= 4)
        count += nibblebits[num & 0x0f];
    return count;
}

从http://ctips.pbwiki.com/CountBits

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。