Question

我正在尝试编写一些常用的实用函数，例如在gcc向量中添加所有元素。

inline float add_all(float const in __attribute__((vector_size(8))))
{
  return in[0] + in[1];
}

inline float add_all(float const in __attribute__((vector_size(16))))
{
  return in[0] + in[1] + in[2] + in[3];
}

inline double add_all(double const in __attribute__((vector_size(16))))
{
  return in[0] + in[1];
}

inline double add_all(double const in __attribute__((vector_size(32))))
{
  return in[0] + in[1] + in[2] + in[3];
}

但是，在编译时，gcc对象：

In file included from matrix.hpp:5:0,
                 from matrix.cpp:3:
vector.hpp:22:1: error: 'float vxl::add_all(__vector(4) float)' conflicts with a previous declaration
 }
 ^
vector.hpp:14:14: note: previous declaration 'float vxl::add_all(__vector(2) float)'
 inline float add_all(float const in __attribute__((vector_size(8))))
              ^
vector.hpp:19:14: note: -fabi-version=6 (or =0) avoids this error with a change in mangling
 inline float add_all(float const in __attribute__((vector_size(16))))
              ^
vector.hpp:32:1: error: 'double vxl::add_all(__vector(4) double)' conflicts with a previous declaration
 }
 ^
vector.hpp:24:15: note: previous declaration 'double vxl::add_all(__vector(2) double)'
 inline double add_all(double const in __attribute__((vector_size(16))))
               ^
vector.hpp:29:15: note: -fabi-version=6 (or =0) avoids this error with a change in mangling
 inline double add_all(double const in __attribute__((vector_size(32))))

除了gcc建议的解决方法之外，是否存在解决方法？

Answer 1

提供一个额外的默认参数，为函数提供不同的错位名称：

typedef float __attribute__((vector_size(8))) vector_f8;
typedef float __attribute__((vector_size(16))) vector_f16;
typedef double __attribute__((vector_size(16))) vector_d16;
typedef double __attribute__((vector_size(32))) vector_d32;

template <int _len>
struct vector_len {
    static int const len = _len;
};

float
add_all(vector_f8 in, vector_len<8> *_p = NULL) {
    return in[0] + in[1];
}

float
add_all(vector_f16 in, vector_len<16> *_p = NULL) {
    return in[0] + in[1] + in[2] + in[3];
}

float
add_all(vector_d16 in, vector_len<16> *_p = NULL) {
    return in[0] + in[1];
}

float
add_all(vector_d32 in, vector_len<32> *_p = NULL) {
    return in[0] + in[1] + in[2] + in[3];
}

如何重载参数仅由gcc向量扩展vector_size属性不同的函数？

1 个答案: