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;
}

/*
** 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。

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

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

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。