/*
** http://graphics.stanford.edu/~seander/bithacks.html#IntegerLog
*/
#define __LOG2A(s) ((s &0xffffffff00000000) ? (32 +__LOG2B(s >>32)): (__LOG2B(s)))
#define __LOG2B(s) ((s &0xffff0000)         ? (16 +__LOG2C(s >>16)): (__LOG2C(s)))
#define __LOG2C(s) ((s &0xff00)             ? (8  +__LOG2D(s >>8)) : (__LOG2D(s)))
#define __LOG2D(s) ((s &0xf0)               ? (4  +__LOG2E(s >>4)) : (__LOG2E(s)))
#define __LOG2E(s) ((s &0xc)                ? (2  +__LOG2F(s >>2)) : (__LOG2F(s)))
#define __LOG2F(s) ((s &0x2)                ? (1)                  : (0))

#define LOG2_UINT64 __LOG2A
#define LOG2_UINT32 __LOG2B
#define LOG2_UINT16 __LOG2C
#define LOG2_UINT8  __LOG2D

static inline uint64_t
next_power_of_2(uint64_t i)
{
#if defined(__GNUC__)
    return 1UL <<(1 +(63 -__builtin_clzl(i -1)));
#else
    i =i -1;
    i =LOG2_UINT64(i);
    return 1UL <<(1 +i);
#endif
}

如果你不想冒险进入未定义行为的领域，输入值必须在1到2^63之间。宏在编译时设置常量也很有用。

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。

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。

对于任何unsigned类型，构建在Bit Twiddling Hacks上:

#include <climits>
#include <type_traits>

template <typename UnsignedType>
UnsignedType round_up_to_power_of_2(UnsignedType v) {
  static_assert(std::is_unsigned<UnsignedType>::value, "Only works for unsigned types");
  v--;
  for (size_t i = 1; i < sizeof(v) * CHAR_BIT; i *= 2) //Prefer size_t "Warning comparison between signed and unsigned integer"
  {
    v |= v >> i;
  }
  return ++v;
}

这里并没有真正的循环，因为编译器在编译时知道迭代的次数。

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;
}

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