我想写一个函数,返回最接近的2的次幂数。例如,如果我的输入是789,输出应该是1024。有没有办法不使用任何循环,而只是使用一些位运算符?
当前回答
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。
其他回答
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));
}
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。
将其转换为浮点数,然后使用.hex()来显示标准化的IEEE表示。
> > >(789)浮动.hex () “0 x1.8a80000000000p + 9”
然后提取指数,再加1。
>>> int(float(789).hex().split('p+')[1]) + 1 10
取2的这个次方。
> > > 2 * * (int (float(789)。hex(),斯普利特(“p +”)[1])+ 1) 1024
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
}
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;
}