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;
}

原生ARM指令“rbit”可以用1个cpu周期和1个额外的cpu寄存器来完成，不可能被击败。

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

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;
}

// Purpose: to reverse bits in an unsigned short integer 
// Input: an unsigned short integer whose bits are to be reversed
// Output: an unsigned short integer with the reversed bits of the input one
unsigned short ReverseBits( unsigned short a )
{
     // declare and initialize number of bits in the unsigned short integer
     const char num_bits = sizeof(a) * CHAR_BIT;

     // declare and initialize bitset representation of integer a
     bitset<num_bits> bitset_a(a);          

     // declare and initialize bitset representation of integer b (0000000000000000)
     bitset<num_bits> bitset_b(0);                  

     // declare and initialize bitset representation of mask (0000000000000001)
     bitset<num_bits> mask(1);          

     for ( char i = 0; i < num_bits; ++i )
     {
          bitset_b = (bitset_b << 1) | bitset_a & mask;
          bitset_a >>= 1;
     }

     return (unsigned short) bitset_b.to_ulong();
}

void PrintBits( unsigned short a )
{
     // declare and initialize bitset representation of a
     bitset<sizeof(a) * CHAR_BIT> bitset(a);

     // print out bits
     cout << bitset << endl;
}


// Testing the functionality of the code

int main ()
{
     unsigned short a = 17, b;

     cout << "Original: "; 
     PrintBits(a);

     b = ReverseBits( a );

     cout << "Reversed: ";
     PrintBits(b);
}

// Output:
Original: 0000000000010001
Reversed: 1000100000000000

我认为下面是我所知道的最简单的方法。MSB是输入，LSB是“反向”输出:

unsigned char rev(char MSB) {
    unsigned char LSB=0;  // for output
    _FOR(i,0,8) {
        LSB= LSB << 1;
        if(MSB&1) LSB = LSB | 1;
        MSB= MSB >> 1;
    }
    return LSB;
}

//    It works by rotating bytes in opposite directions. 
//    Just repeat for each byte.