/*
** 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。

假设你有一个好的编译器&它可以做bit twiddling在这一点上我以上，但无论如何这是工作!!

    // http://graphics.stanford.edu/~seander/bithacks.html#IntegerLogObvious
    #define SH1(v)  ((v-1) | ((v-1) >> 1))            // accidently came up w/ this...
    #define SH2(v)  ((v) | ((v) >> 2))
    #define SH4(v)  ((v) | ((v) >> 4))
    #define SH8(v)  ((v) | ((v) >> 8))
    #define SH16(v) ((v) | ((v) >> 16))
    #define OP(v) (SH16(SH8(SH4(SH2(SH1(v))))))         

    #define CB0(v)   ((v) - (((v) >> 1) & 0x55555555))
    #define CB1(v)   (((v) & 0x33333333) + (((v) >> 2) & 0x33333333))
    #define CB2(v)   ((((v) + ((v) >> 4) & 0xF0F0F0F) * 0x1010101) >> 24)
    #define CBSET(v) (CB2(CB1(CB0((v)))))
    #define FLOG2(v) (CBSET(OP(v)))

测试代码如下:

#include <iostream>

using namespace std;

// http://graphics.stanford.edu/~seander/bithacks.html#IntegerLogObvious
#define SH1(v)  ((v-1) | ((v-1) >> 1))  // accidently guess this...
#define SH2(v)  ((v) | ((v) >> 2))
#define SH4(v)  ((v) | ((v) >> 4))
#define SH8(v)  ((v) | ((v) >> 8))
#define SH16(v) ((v) | ((v) >> 16))
#define OP(v) (SH16(SH8(SH4(SH2(SH1(v))))))         

#define CB0(v)   ((v) - (((v) >> 1) & 0x55555555))
#define CB1(v)   (((v) & 0x33333333) + (((v) >> 2) & 0x33333333))
#define CB2(v)   ((((v) + ((v) >> 4) & 0xF0F0F0F) * 0x1010101) >> 24)
#define CBSET(v) (CB2(CB1(CB0((v)))))
#define FLOG2(v) (CBSET(OP(v))) 

#define SZ4         FLOG2(4)
#define SZ6         FLOG2(6)
#define SZ7         FLOG2(7)
#define SZ8         FLOG2(8) 
#define SZ9         FLOG2(9)
#define SZ16        FLOG2(16)
#define SZ17        FLOG2(17)
#define SZ127       FLOG2(127)
#define SZ1023      FLOG2(1023)
#define SZ1024      FLOG2(1024)
#define SZ2_17      FLOG2((1ul << 17))  // 
#define SZ_LOG2     FLOG2(SZ)

#define DBG_PRINT(x) do { std::printf("Line:%-4d" "  %10s = %-10d\n", __LINE__, #x, x); } while(0);

uint32_t arrTble[FLOG2(63)];

int main(){
    int8_t n;

    DBG_PRINT(SZ4);    
    DBG_PRINT(SZ6);    
    DBG_PRINT(SZ7);    
    DBG_PRINT(SZ8);    
    DBG_PRINT(SZ9); 
    DBG_PRINT(SZ16);
    DBG_PRINT(SZ17);
    DBG_PRINT(SZ127);
    DBG_PRINT(SZ1023);
    DBG_PRINT(SZ1024);
    DBG_PRINT(SZ2_17);

    return(0);
}

输出:

Line:39           SZ4 = 2
Line:40           SZ6 = 3
Line:41           SZ7 = 3
Line:42           SZ8 = 3
Line:43           SZ9 = 4
Line:44          SZ16 = 4
Line:45          SZ17 = 5
Line:46         SZ127 = 7
Line:47        SZ1023 = 10
Line:48        SZ1024 = 10
Line:49        SZ2_16 = 17

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。

你可能会发现以下的澄清有助于达到你的目的:

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;
    }
}

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。