在x86中，你可以使用sse4位操作指令来提高速度。

//assume input is in eax
mov    ecx,31      
popcnt edx,eax   //cycle 1
lzcnt  eax,eax   //cycle 2
sub    ecx,eax
mov    eax,1
cmp    edx,1     //cycle 3
jle @done        //cycle 4 - popcnt says its a power of 2, return input unchanged
shl    eax,cl    //cycle 5
@done: rep ret   //cycle 5

在c中，您可以使用匹配的intrinsic。

或者无跳转，通过避免跳转导致的错误预测来加快速度，但通过延长依赖链来减慢速度。计时，看看哪种代码最适合您。

//assume input is in eax
mov    ecx,31
popcnt edx,eax    //cycle 1
lzcnt  eax,eax
sub    ecx,eax
mov    eax,1      //cycle 2
cmp    edx,1
mov    edx,0     //cycle 3 
cmovle ecx,edx   //cycle 4 - ensure eax does not change
shl    eax,cl    
@done: rep ret   //cycle 5

unsigned long upper_power_of_two(unsigned long v)
{
    v--;
    v |= v >> 1;
    v |= v >> 2;
    v |= v >> 4;
    v |= v >> 8;
    v |= v >> 16;
    v++;
    return v;

}

如果你需要OpenGL相关的东西:

/* Compute the nearest power of 2 number that is 
 * less than or equal to the value passed in. 
 */
static GLuint 
nearestPower( GLuint value )
{
    int i = 1;

    if (value == 0) return -1;      /* Error! */
    for (;;) {
         if (value == 1) return i;
         else if (value == 3) return i*4;
         value >>= 1; i *= 2;
    }
}

为了完整起见，这里是用标准C语言实现的浮点数。

double next_power_of_two(double value) {
    int exp;
    if(frexp(value, &exp) == 0.5) {
        // Omit this case to round precise powers of two up to the *next* power
        return value;
    }
    return ldexp(1.0, exp);
}

g++编译器提供了一个内置函数__builtin_clz，用于计算前导零:

所以我们可以这样做:

int nextPowerOfTwo(unsigned int x) {
  return 1 << sizeof(x)*8 - __builtin_clz(x);
}

int main () {
  std::cout << nextPowerOfTwo(7)  << std::endl;
  std::cout << nextPowerOfTwo(31) << std::endl;
  std::cout << nextPowerOfTwo(33) << std::endl;
  std::cout << nextPowerOfTwo(8)  << std::endl;
  std::cout << nextPowerOfTwo(91) << std::endl;
  
  return 0;
}

结果:

8
32
64
16
128

但请注意，对于x == 0， __builtin_clz return是未定义的。

from math import ceil, log2
pot_ceil = lambda N: 0x1 << ceil(log2(N))

测试:

for i in range(10):
    print(i, pot_ceil(i))

输出:

1 1
2 2
3 4
4 4
5 8
6 8
7 8
8 8
9 16
10 16