c++ 14 clp2的constexpr版本

#include <iostream>
#include <type_traits>

// Closest least power of 2 minus 1. Returns 0 if n = 0.
template <typename UInt, std::enable_if_t<std::is_unsigned<UInt>::value,int> = 0>
  constexpr UInt clp2m1(UInt n, unsigned i = 1) noexcept
    { return i < sizeof(UInt) * 8 ? clp2m1(UInt(n | (n >> i)),i << 1) : n; }

/// Closest least power of 2 minus 1. Returns 0 if n <= 0.
template <typename Int, std::enable_if_t<std::is_integral<Int>::value && std::is_signed<Int>::value,int> = 0>
  constexpr auto clp2m1(Int n) noexcept
    { return clp2m1(std::make_unsigned_t<Int>(n <= 0 ? 0 : n)); }

/// Closest least power of 2. Returns 2^N: 2^(N-1) < n <= 2^N. Returns 0 if n <= 0.
template <typename Int, std::enable_if_t<std::is_integral<Int>::value,int> = 0>
  constexpr auto clp2(Int n) noexcept
    { return clp2m1(std::make_unsigned_t<Int>(n-1)) + 1; }

/// Next power of 2. Returns 2^N: 2^(N-1) <= n < 2^N. Returns 1 if n = 0. Returns 0 if n < 0.
template <typename Int, std::enable_if_t<std::is_integral<Int>::value,int> = 0>
  constexpr auto np2(Int n) noexcept
    { return clp2m1(std::make_unsigned_t<Int>(n)) + 1; }

template <typename T>
  void test(T v) { std::cout << clp2(v) << std::endl; }

int main()
{
    test(-5);                          // 0
    test(0);                           // 0
    test(8);                           // 8
    test(31);                          // 32
    test(33);                          // 64
    test(789);                         // 1024
    test(char(260));                   // 4
    test(unsigned(-1) - 1);            // 0
    test<long long>(unsigned(-1) - 1); // 4294967296

    return 0;
}

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;
    }
}

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
}

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。

检查Bit Twiddling Hacks。你需要得到以2为底的对数，然后加上1。32位值的示例:

四舍五入到下一个2的最高次幂 Unsigned int v;//计算32位v的下一个最高次幂2 v -; V |= V >> 1; V |= V >> 2; V |= V >> 4; V |= V >> 8; V |= V >> 16; v + +;

延伸到其他宽度应该是明显的。

如果您正在使用GCC，您可能想要看看Lockless Inc.优化next_pow2()函数。本页描述了一种使用内置函数builtin_clz()(计数前导零)的方法，然后直接使用x86 (ia32)汇编指令bsr(位扫描反向)，就像它在另一个答案的游戏开发站点链接中所描述的那样。此代码可能比前面的回答中描述的更快。

顺便说一下，如果你不打算使用汇编指令和64位数据类型，你可以使用这个

/**
 * return the smallest power of two value
 * greater than x
 *
 * Input range:  [2..2147483648]
 * Output range: [2..2147483648]
 *
 */
__attribute__ ((const))
static inline uint32_t p2(uint32_t x)
{
#if 0
    assert(x > 1);
    assert(x <= ((UINT32_MAX/2) + 1));
#endif

    return 1 << (32 - __builtin_clz (x - 1));
}