import sys


def is_power2(x):
    return x > 0 and ((x & (x - 1)) == 0)


def find_nearest_power2(x):
    if x <= 0:
        raise ValueError("invalid input")
    if is_power2(x):
        return x
    else:
        bits = get_bits(x)
        upper = 1 << (bits)
        lower = 1 << (bits - 1)
        mid = (upper + lower) // 2
        if (x - mid) > 0:
            return upper
        else:
            return lower


def get_bits(x):
    """return number of bits in binary representation"""
    if x < 0:
        raise ValueError("invalid input: input should be positive integer")
    count = 0
    while (x != 0):
        try:
            x = x >> 1
        except TypeError as error:
            print(error, "input should be of type integer")
            sys.exit(1)
        count += 1
    return count

对于IEEE浮点，你可以这样做。

int next_power_of_two(float a_F){
    int f = *(int*)&a_F;
    int b = f << 9 != 0; // If we're a power of two this is 0, otherwise this is 1

    f >>= 23; // remove factional part of floating point number
    f -= 127; // subtract 127 (the bias) from the exponent

    // adds one to the exponent if were not a power of two, 
    // then raises our new exponent to the power of two again.
    return (1 << (f + b)); 
}

如果你需要一个整数的解决方案，并且你能够使用内联汇编，BSR会在x86上给你一个整数的log2。它计算有多少位是正确的，这正好等于这个数字的log2。其他处理器(通常)有类似的指令，比如CLZ，根据你的编译器，可能有一个内在的可用指令来为你做这项工作。

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

试图为这个问题找到一个“终极”解决方案。下面的代码

针对的是C语言(不是c++)， 使用编译器内置生成有效的代码(CLZ或BSR指令)，如果编译器支持任何， 是便携式的(标准C和没有汇编)，除了内置，和 处理所有未定义的行为。

如果你用c++编写，你可以适当地调整代码。注意，c++ 20引入了std::bit_ceil，它做了完全相同的事情，只是在某些条件下行为可能是未定义的。

#include <limits.h>

#ifdef _MSC_VER
# if _MSC_VER >= 1400
/* _BitScanReverse is introduced in Visual C++ 2005 and requires
   <intrin.h> (also introduced in Visual C++ 2005). */
#include <intrin.h>
#pragma intrinsic(_BitScanReverse)
#pragma intrinsic(_BitScanReverse64)
#  define HAVE_BITSCANREVERSE 1
# endif
#endif

/* Macro indicating that the compiler supports __builtin_clz().
   The name HAVE_BUILTIN_CLZ seems to be the most common, but in some
   projects HAVE__BUILTIN_CLZ is used instead. */
#ifdef __has_builtin
# if __has_builtin(__builtin_clz)
#  define HAVE_BUILTIN_CLZ 1
# endif
#elif defined(__GNUC__)
# if (__GNUC__ > 3)
#  define HAVE_BUILTIN_CLZ 1
# elif defined(__GNUC_MINOR__)
#  if (__GNUC__ == 3 && __GNUC_MINOR__ >= 4)
#   define HAVE_BUILTIN_CLZ 1
#  endif
# endif
#endif

/**
 * Returns the smallest power of two that is not smaller than x.
 */
unsigned long int next_power_of_2_long(unsigned long int x)
{
    if (x <= 1) {
        return 1;
    }
    x--;

#ifdef HAVE_BITSCANREVERSE
    if (x > (ULONG_MAX >> 1)) {
        return 0;
    } else {
        unsigned long int index;
        (void) _BitScanReverse(&index, x);
        return (1UL << (index + 1));
    }
#elif defined(HAVE_BUILTIN_CLZ)
    if (x > (ULONG_MAX >> 1)) {
        return 0;
    }
    return (1UL << (sizeof(x) * CHAR_BIT - __builtin_clzl(x)));
#else
    /* Solution from "Bit Twiddling Hacks"
       <http://www.graphics.stanford.edu/~seander/bithacks.html#RoundUpPowerOf2>
       but converted to a loop for smaller code size.
       ("gcc -O3" will unroll this.) */
    {
        unsigned int shift;
        for (shift = 1; shift < sizeof(x) * CHAR_BIT; shift <<= 1) {
            x |= (x >> shift);
        }
    }
    return (x + 1);
#endif
}

unsigned int next_power_of_2(unsigned int x)
{
    if (x <= 1) {
        return 1;
    }
    x--;

#ifdef HAVE_BITSCANREVERSE
    if (x > (UINT_MAX >> 1)) {
        return 0;
    } else {
        unsigned long int index;
        (void) _BitScanReverse(&index, x);
        return (1U << (index + 1));
    }
#elif defined(HAVE_BUILTIN_CLZ)
    if (x > (UINT_MAX >> 1)) {
        return 0;
    }
    return (1U << (sizeof(x) * CHAR_BIT - __builtin_clz(x)));
#else
    {
        unsigned int shift;
        for (shift = 1; shift < sizeof(x) * CHAR_BIT; shift <<= 1) {
            x |= (x >> shift);
        }
    }
    return (x + 1);
#endif
}

unsigned long long next_power_of_2_long_long(unsigned long long x)
{
    if (x <= 1) {
        return 1;
    }
    x--;

#if (defined(HAVE_BITSCANREVERSE) && \
    ULLONG_MAX == 18446744073709551615ULL)
    if (x > (ULLONG_MAX >> 1)) {
        return 0;
    } else {
        /* assert(sizeof(__int64) == sizeof(long long)); */
        unsigned long int index;
        (void) _BitScanReverse64(&index, x);
        return (1ULL << (index + 1));
    }
#elif defined(HAVE_BUILTIN_CLZ)
    if (x > (ULLONG_MAX >> 1)) {
        return 0;
    }
    return (1ULL << (sizeof(x) * CHAR_BIT - __builtin_clzll(x)));
#else
    {
        unsigned int shift;
        for (shift = 1; shift < sizeof(x) * CHAR_BIT; shift <<= 1) {
            x |= (x >> shift);
        }
    }
    return (x + 1);
#endif
}

将保罗·迪克森的答案应用到Excel中，效果非常好。

 =POWER(2,CEILING.MATH(LOG(A1)/LOG(2)))

许多处理器架构都支持log以2为底或非常类似的操作——计数前导零。许多编译器都有针对它的内在特性。参见https://en.wikipedia.org/wiki/Find_first_set