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;
}

C / c++中用于整数输入的高效微软(例如Visual Studio 2017)特定解决方案。在检查最有效的1位的位置之前，通过递减处理输入完全匹配2的幂值的情况。

inline unsigned int ExpandToPowerOf2(unsigned int Value)
{
    unsigned long Index;
    _BitScanReverse(&Index, Value - 1);
    return (1U << (Index + 1));
}

// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

#if defined(WIN64) // The _BitScanReverse64 intrinsic is only available for 64 bit builds because it depends on x64

inline unsigned long long ExpandToPowerOf2(unsigned long long Value)
{
    unsigned long Index;
    _BitScanReverse64(&Index, Value - 1);
    return (1ULL << (Index + 1));
}

#endif

这将为英特尔处理器生成5个左右的内联指令，类似如下:

dec eax
bsr rcx, rax
inc ecx
mov eax, 1
shl rax, cl

显然Visual Studio c++编译器并没有针对编译时值进行优化，但这里并没有大量的指令。

编辑:

如果你想让输入值1产生1(2的0次方)，对上面代码的一个小修改仍然会生成没有分支的直通指令。

inline unsigned int ExpandToPowerOf2(unsigned int Value)
{
    unsigned long Index;
    _BitScanReverse(&Index, --Value);
    if (Value == 0)
        Index = (unsigned long) -1;
    return (1U << (Index + 1));
}

生成更多的指令。诀窍在于Index可以被一个测试后跟一个cmove指令所取代。

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;
    }
}

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));
}

我试着找到最接近2的次幂，然后写出这个函数。希望它能帮助你。只要用最近的小数乘以2，就能得到2的最近上次方

int nearest_upper_power(int number){
    int temp=number;
    while((number&(number-1))!=0){
        temp<<=1;
        number&=temp;
    }
    //Here number is closest lower power 
    number*=2;
    return number;
}