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
尽管问题标注为c,我的5分钱。幸运的是,c++ 20将包含std::ceil2和std::floor2(参见这里)。它是consexpr模板函数,目前的GCC实现使用位移位和工作于任何整型无符号类型。
其他回答
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;
}
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;
}
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
为了完整起见,这里是用标准C语言实现的浮点数。
double next_power_of_two(double value) {
int exp;
if(frexp(value, &exp) == 0.5) {
// Omit this case to round precise powers of two up to the *next* power
return value;
}
return ldexp(1.0, exp);
}
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