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];
}

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

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;
  }

我使用下面的函数。我还没有检查基准测试，但它是有效的。

int msb(int num)
{
    int m = 0;
    for (int i = 16; i > 0; i = i>>1)
    {
        // debug(i, num, m);
        if(num>>i)
        {
            m += i;
            num>>=i;
        }
    }
    return m;
}

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;
}
}

这是在golang中的实现

func CountBitSet(n int) int {


    count := 0
    for n > 0 {
      count += n & 1
      n >>= 1

    }
    return count
}