对于其他可能遇到这个问题的网络搜索者，这里有一个总结(针对C和JavaScript)。

对于JavaScript的完整解决方案，我们可以首先生成表:

const BIT_REVERSAL_TABLE = new Array(256)

for (var i = 0; i < 256; ++i) {
  var v = i, r = i, s = 7;
  for (v >>>= 1; v; v >>>= 1) {
    r <<= 1;
    r |= v & 1;
    --s;
  }
  BIT_REVERSAL_TABLE[i] = (r << s) & 0xff;
}

这给了我们BIT_REVERSAL_TABLE，这是@MattJ发布的:

const BIT_REVERSAL_TABLE = new Uint8Array([      
  0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0, 
  0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8, 0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8, 
  0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4, 0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4, 
  0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec, 0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc, 
  0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2, 0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2, 
  0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea, 0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
  0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6, 0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6, 
  0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee, 0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
  0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1, 0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
  0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9, 0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9, 
  0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5, 0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
  0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed, 0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
  0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3, 0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3, 
  0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb, 0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
  0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7, 0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7, 
  0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef, 0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff
])

8位、16位和32位无符号整数的算法可以在这里找到:

function reverseBits8(n) {
  return BIT_REVERSAL_TABLE[n]
}

function reverseBits16(n) {
  return (BIT_REVERSAL_TABLE[(n >> 8) & 0xff] |
    BIT_REVERSAL_TABLE[n & 0xff] << 8)
}

function reverseBits32(n) {
  return (BIT_REVERSAL_TABLE[n & 0xff] << 24) |
    (BIT_REVERSAL_TABLE[(n >>> 8) & 0xff] << 16) |
    (BIT_REVERSAL_TABLE[(n >>> 16) & 0xff] << 8) |
    BIT_REVERSAL_TABLE[(n >>> 24) & 0xff];
}

注意，32位版本不能在JavaScript中工作(必须转换为使用bigint，这很简单)，但应该可以在64位语言中工作:

log8(0b11000100)
log16(0b1110001001001100)
log32(0b11110010111110111100110010101011)

// 0b11000100 => 0b00100011
// 0b1110001001001100 => 0b0011001001000111
// doesn't work in JS it seems:
// 0b11110010111110111100110010101011 => 0b0-101010110011000010000010110001

function log8(n) {
  console.log(`${bits(n, 8)} => ${bits(reverseBits8(n), 8)}`)
}

function log16(n) {
  console.log(`${bits(n, 16)} => ${bits(reverseBits16(n), 16)}`)
}

function log32(n) {
  console.log(`${bits(n, 32)} => ${bits(reverseBits32(n), 32)}`)
}

function bits(n, size) {
  return `0b${n.toString(2).padStart(size, '0')}`
}

注意:这个解决方案适用于JavaScript的32位:

function reverseBits32(n) {
  let res = 0;
  for (let i = 0; i < 32; i++) {
    res = (res << 1) + (n & 1);
    n = n >>> 1;
  }

  return res >>> 0;
}

所有3个基于表格的解决方案都可以在C中正常工作。下面是一个粗略的C版本:

#include <stdlib.h>

static uint8_t* BIT_REVERSAL_TABLE;

uint8_t* 
make_bit_reversal_table() {
  uint8_t *table = malloc(256 * sizeof(uint8_t));
  uint8_t i;
  for (i = 0; i < 256 ; ++i) {
    uint8_t v = i;
    uint8_t r = i;
    uint8_t s = 7;
    for (v = v >> 1; v; v = v >> 1) {
      r <<= 1;
      r |= v & 1;
      --s;
    }
    table[i] = (r << s) & 0xff;
  }
  return table;
}

uint8_t 
reverse_bits_8(uint8_t n) {
  return BIT_REVERSAL_TABLE[n];
}

uint16_t
reverse_bits_16(uint16_t n)
{
  return (BIT_REVERSAL_TABLE[(n >> 8) & 0xff]
    | BIT_REVERSAL_TABLE[n & 0xff] << 8);
}

uint32_t
reverse_bits_32(uint32_t n) {
  return (BIT_REVERSAL_TABLE[n & 0xff] << 24) 
    | (BIT_REVERSAL_TABLE[(n >> 8) & 0xff] << 16) 
    | (BIT_REVERSAL_TABLE[(n >> 16) & 0xff] << 8) 
    | BIT_REVERSAL_TABLE[(n >> 24) & 0xff];
}

int 
main(void) {
  BIT_REVERSAL_TABLE = make_bit_reversal_table();
  return 0;
}

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);
}

似乎许多其他帖子都关心速度(即最好=最快)。 简单性怎么样?考虑:

char ReverseBits(char character) {
    char reversed_character = 0;
    for (int i = 0; i < 8; i++) {
        char ith_bit = (c >> i) & 1;
        reversed_character |= (ith_bit << (sizeof(char) - 1 - i));
    }
    return reversed_character;
}

并希望聪明的编译器将为您优化。

如果你想反转一个更长的位列表(包含sizeof(char) * n位)，你可以使用这个函数得到:

void ReverseNumber(char* number, int bit_count_in_number) {
    int bytes_occupied = bit_count_in_number / sizeof(char);      

    // first reverse bytes
    for (int i = 0; i <= (bytes_occupied / 2); i++) {
        swap(long_number[i], long_number[n - i]);
    }

    // then reverse bits of each individual byte
    for (int i = 0; i < bytes_occupied; i++) {
         long_number[i] = ReverseBits(long_number[i]);
    }
}

这将把[10000000,10101010]反向转换为[01010101,00000001]。

当然，玩弄比特的黑客的明显来源是: http://graphics.stanford.edu/~seander/bithacks.html#BitReverseObvious

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

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;  
 }