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;

}

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
}

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;

}

c#中的可移植解决方案:

int GetNextPowerOfTwo(int input) {
    return 1 << (int)Math.Ceiling(Math.Log2(input));
}

Math.Ceiling(Math.Log2(value))计算2的下一个幂的指数，1 <<通过移位计算实值。

更快的解决方案，如果你有。net Core 3或更高版本:

uint GetNextPowerOfTwoFaster(uint input) {
    return (uint)1 << (sizeof(uint) * 8 - System.Numerics.BitOperations.LeadingZeroCount(input - 1));
}

这将使用system . numbers . bitoperations . leadingzerocount()，如果可用，则使用硬件指令:

https://github.com/dotnet/corert/blob/master/src/System.Private.CoreLib/shared/System/Numerics/BitOperations.cs

更新:

RoundUpToPowerOf2()即将在。net 6!内部实现与上面的. net Core 3解决方案基本相同。

这里是社区更新。

这是我用来让它成为一个常数表达式的，如果输入是一个常数表达式的话。

#define uptopow2_0(v) ((v) - 1)
#define uptopow2_1(v) (uptopow2_0(v) | uptopow2_0(v) >> 1)
#define uptopow2_2(v) (uptopow2_1(v) | uptopow2_1(v) >> 2)
#define uptopow2_3(v) (uptopow2_2(v) | uptopow2_2(v) >> 4)
#define uptopow2_4(v) (uptopow2_3(v) | uptopow2_3(v) >> 8)
#define uptopow2_5(v) (uptopow2_4(v) | uptopow2_4(v) >> 16)

#define uptopow2(v) (uptopow2_5(v) + 1)  /* this is the one programmer uses */

例如，这样的表达式:

uptopow2(sizeof (struct foo))

会很好地化简为常数。