高效意味着吞吐量或延迟。

从头到尾，看看安德斯·塞德罗尼厄斯的回答，很好。

为了降低延迟，我推荐以下代码:

uint32_t reverseBits( uint32_t x )
{
#if defined(__arm__) || defined(__aarch64__)
    __asm__( "rbit %0, %1" : "=r" ( x ) : "r" ( x ) );
    return x;
#endif
    // Flip pairwise
    x = ( ( x & 0x55555555 ) << 1 ) | ( ( x & 0xAAAAAAAA ) >> 1 );
    // Flip pairs
    x = ( ( x & 0x33333333 ) << 2 ) | ( ( x & 0xCCCCCCCC ) >> 2 );
    // Flip nibbles
    x = ( ( x & 0x0F0F0F0F ) << 4 ) | ( ( x & 0xF0F0F0F0 ) >> 4 );

    // Flip bytes. CPUs have an instruction for that, pretty fast one.
#ifdef _MSC_VER
    return _byteswap_ulong( x );
#elif defined(__INTEL_COMPILER)
    return (uint32_t)_bswap( (int)x );
#else
    // Assuming gcc or clang
    return __builtin_bswap32( x );
#endif
}

编译器输出:https://godbolt.org/z/5ehd89

我很好奇原始旋转有多快。 在我的机器(i7@2600)上，1,500,150,000次迭代的平均值为27.28 ns(在131,071个64位整数的随机集上)。

优点:占用内存少，代码简单。我想说它也没有那么大。对于任何输入(128个算术SHIFT运算+ 64个逻辑and运算+ 64个逻辑OR运算)，所需的时间都是可预测的常量。

我比较了@Matt J获得的最佳时间，他有公认的答案。如果我没有看错他的答案，他得到的最好结果是0.631739秒，100万次迭代，这导致平均每次旋转631 ns。

我使用的代码片段如下:

unsigned long long reverse_long(unsigned long long x)
{
    return (((x >> 0) & 1) << 63) |
           (((x >> 1) & 1) << 62) |
           (((x >> 2) & 1) << 61) |
           (((x >> 3) & 1) << 60) |
           (((x >> 4) & 1) << 59) |
           (((x >> 5) & 1) << 58) |
           (((x >> 6) & 1) << 57) |
           (((x >> 7) & 1) << 56) |
           (((x >> 8) & 1) << 55) |
           (((x >> 9) & 1) << 54) |
           (((x >> 10) & 1) << 53) |
           (((x >> 11) & 1) << 52) |
           (((x >> 12) & 1) << 51) |
           (((x >> 13) & 1) << 50) |
           (((x >> 14) & 1) << 49) |
           (((x >> 15) & 1) << 48) |
           (((x >> 16) & 1) << 47) |
           (((x >> 17) & 1) << 46) |
           (((x >> 18) & 1) << 45) |
           (((x >> 19) & 1) << 44) |
           (((x >> 20) & 1) << 43) |
           (((x >> 21) & 1) << 42) |
           (((x >> 22) & 1) << 41) |
           (((x >> 23) & 1) << 40) |
           (((x >> 24) & 1) << 39) |
           (((x >> 25) & 1) << 38) |
           (((x >> 26) & 1) << 37) |
           (((x >> 27) & 1) << 36) |
           (((x >> 28) & 1) << 35) |
           (((x >> 29) & 1) << 34) |
           (((x >> 30) & 1) << 33) |
           (((x >> 31) & 1) << 32) |
           (((x >> 32) & 1) << 31) |
           (((x >> 33) & 1) << 30) |
           (((x >> 34) & 1) << 29) |
           (((x >> 35) & 1) << 28) |
           (((x >> 36) & 1) << 27) |
           (((x >> 37) & 1) << 26) |
           (((x >> 38) & 1) << 25) |
           (((x >> 39) & 1) << 24) |
           (((x >> 40) & 1) << 23) |
           (((x >> 41) & 1) << 22) |
           (((x >> 42) & 1) << 21) |
           (((x >> 43) & 1) << 20) |
           (((x >> 44) & 1) << 19) |
           (((x >> 45) & 1) << 18) |
           (((x >> 46) & 1) << 17) |
           (((x >> 47) & 1) << 16) |
           (((x >> 48) & 1) << 15) |
           (((x >> 49) & 1) << 14) |
           (((x >> 50) & 1) << 13) |
           (((x >> 51) & 1) << 12) |
           (((x >> 52) & 1) << 11) |
           (((x >> 53) & 1) << 10) |
           (((x >> 54) & 1) << 9) |
           (((x >> 55) & 1) << 8) |
           (((x >> 56) & 1) << 7) |
           (((x >> 57) & 1) << 6) |
           (((x >> 58) & 1) << 5) |
           (((x >> 59) & 1) << 4) |
           (((x >> 60) & 1) << 3) |
           (((x >> 61) & 1) << 2) |
           (((x >> 62) & 1) << 1) |
           (((x >> 63) & 1) << 0);
}

好吧，这基本上与第一个“reverse()”相同，但它是64位的，只需要从指令流中加载一个即时掩码。GCC创建的代码没有跳转，所以这应该是相当快的。

#include <stdio.h>

static unsigned long long swap64(unsigned long long val)
{
#define ZZZZ(x,s,m) (((x) >>(s)) & (m)) | (((x) & (m))<<(s));
/* val = (((val) >>16) & 0xFFFF0000FFFF) | (((val) & 0xFFFF0000FFFF)<<16); */

val = ZZZZ(val,32,  0x00000000FFFFFFFFull );
val = ZZZZ(val,16,  0x0000FFFF0000FFFFull );
val = ZZZZ(val,8,   0x00FF00FF00FF00FFull );
val = ZZZZ(val,4,   0x0F0F0F0F0F0F0F0Full );
val = ZZZZ(val,2,   0x3333333333333333ull );
val = ZZZZ(val,1,   0x5555555555555555ull );

return val;
#undef ZZZZ
}

int main(void)
{
unsigned long long val, aaaa[16] =
 { 0xfedcba9876543210,0xedcba9876543210f,0xdcba9876543210fe,0xcba9876543210fed
 , 0xba9876543210fedc,0xa9876543210fedcb,0x9876543210fedcba,0x876543210fedcba9
 , 0x76543210fedcba98,0x6543210fedcba987,0x543210fedcba9876,0x43210fedcba98765
 , 0x3210fedcba987654,0x210fedcba9876543,0x10fedcba98765432,0x0fedcba987654321
 };
unsigned iii;

for (iii=0; iii < 16; iii++) {
    val = swap64 (aaaa[iii]);
    printf("A[]=%016llX Sw=%016llx\n", aaaa[iii], val);
    }
return 0;
}

unsigned char ReverseBits(unsigned char data)
{
    unsigned char k = 0, rev = 0;

    unsigned char n = data;

    while(n)

    {
        k = n & (~(n - 1));
        n &= (n - 1);
        rev |= (128 / k);
    }
    return rev;
}

您可能希望使用标准模板库。它可能比上面提到的代码慢。然而，在我看来，这似乎更清楚，更容易理解。

 #include<bitset>
 #include<iostream>


 template<size_t N>
 const std::bitset<N> reverse(const std::bitset<N>& ordered)
 {
      std::bitset<N> reversed;
      for(size_t i = 0, j = N - 1; i < N; ++i, --j)
           reversed[j] = ordered[i];
      return reversed;
 };


 // test the function
 int main()
 {
      unsigned long num; 
      const size_t N = sizeof(num)*8;

      std::cin >> num;
      std::cout << std::showbase << std::hex;
      std::cout << "ordered  = " << num << std::endl;
      std::cout << "reversed = " << reverse<N>(num).to_ulong()  << std::endl;
      std::cout << "double_reversed = " << reverse<N>(reverse<N>(num)).to_ulong() << std::endl;  
 }

对于喜欢递归的人来说，这是另一个解决方案。

这个想法很简单。 将输入除以一半并交换两部分，继续直到达到单个位。

Illustrated in the example below.

Ex : If Input is 00101010   ==> Expected output is 01010100

1. Divide the input into 2 halves 
    0010 --- 1010

2. Swap the 2 Halves
    1010     0010

3. Repeat the same for each half.
    10 -- 10 ---  00 -- 10
    10    10      10    00

    1-0 -- 1-0 --- 1-0 -- 0-0
    0 1    0 1     0 1    0 0

Done! Output is 01010100

这里有一个递归函数来求解。(注意，我使用了unsigned int，所以它可以用于sizeof(unsigned int)*8位的输入。

递归函数有两个参数-需要位的值 要反转的值和值中的比特数。

int reverse_bits_recursive(unsigned int num, unsigned int numBits)
{
    unsigned int reversedNum;;
    unsigned int mask = 0;

    mask = (0x1 << (numBits/2)) - 1;

    if (numBits == 1) return num;
    reversedNum = reverse_bits_recursive(num >> numBits/2, numBits/2) |
                   reverse_bits_recursive((num & mask), numBits/2) << numBits/2;
    return reversedNum;
}

int main()
{
    unsigned int reversedNum;
    unsigned int num;

    num = 0x55;
    reversedNum = reverse_bits_recursive(num, 8);
    printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);

    num = 0xabcd;
    reversedNum = reverse_bits_recursive(num, 16);
    printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);

    num = 0x123456;
    reversedNum = reverse_bits_recursive(num, 24);
    printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);

    num = 0x11223344;
    reversedNum = reverse_bits_recursive(num,32);
    printf ("Bit Reversal Input = 0x%x Output = 0x%x\n", num, reversedNum);
}

输出如下:

Bit Reversal Input = 0x55 Output = 0xaa
Bit Reversal Input = 0xabcd Output = 0xb3d5
Bit Reversal Input = 0x123456 Output = 0x651690
Bit Reversal Input = 0x11223344 Output = 0x22cc4488