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
这是我用c语言的解决方案，希望能有所帮助!
int next_power_of_two(int n) {
int i = 0;
for (--n; n > 0; n >>= 1) {
i++;
}
return 1 << i;
}
其他回答
unsigned long upper_power_of_two(unsigned long v)
{
v--;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
v++;
return v;
}
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
这是我用c语言的解决方案，希望能有所帮助!
int next_power_of_two(int n) {
int i = 0;
for (--n; n > 0; n >>= 1) {
i++;
}
return 1 << i;
}
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
}
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
