Performance with Yeppp! is slower than native implementation

Question

Hi I am trying to improve the performance of vector algebra in my code using Yeppp! library however the performance is actually getting worse... Here is a piece of the Vector class code:

#include "Vector3.h"
#include <cmath>
#include "yepCore.h"

Vector3::Vector3()
{
    //ctor
}

Vector3::~Vector3()
{
    //dtor
}

Vector3::Vector3(float X, float Y, float Z)
{
    x = X;
    y = Y;
    z = Z;
}


float& Vector3::operator[](int idx)
{
    return (&x)[idx];
}

Vector3& Vector3::normalize()
{
#if USE_YEPPP
    float inf;
    yepCore_SumSquares_V32f_S32f(&x, &inf, 3);
    yepCore_Multiply_IV32fS32f_IV32f(&x, 1.0f / sqrt(inf), 3);
#else
    float inf = 1.0f / sqrt((x * x) + (y * y) + (z * z));
    x *= inf;
    y *= inf;
    z *= inf;
#endif
    return *this;

}

Vector3 Vector3::cross(Vector3& rh)
{
    return Vector3 (
                (y * rh.z) - (z * rh.y),
                (z * rh.x) - (x * rh.z),
                (x * rh.y) - (y * rh.x)
    );
}

float Vector3::dot(Vector3& rh)
{
#if USE_YEPPP
    float ret = 0;
    yepCore_DotProduct_V32fV32f_S32f(&x, &rh.x, &ret, 3);
    return ret;
#else
    return x*rh.x+y*rh.y+z*rh.z;
#endif
}

Vector3 Vector3::operator*(float scalar)
{
#if USE_YEPPP
    Vector3 ret;
    yepCore_Multiply_V32fS32f_V32f(&x, scalar, &ret.x , 3);
    return ret;
#else
    return Vector3(x*scalar, y*scalar,z*scalar);
#endif
}

Vector3 Vector3::operator+(Vector3 rh)
{
#if USE_YEPPP
    Vector3 ret;
    yepCore_Add_V32fV32f_V32f(&x, &rh.x, &ret.x, 3);
    return ret;
#else
    return Vector3(x+rh.x, y+rh.y, z+rh.z);
#endif
}

Vector3 Vector3::operator-(Vector3 rh)
{
#if USE_YEPPP
    Vector3 ret;
    yepCore_Subtract_V32fV32f_V32f(&x, &rh.x, &ret.x, 3);
    return ret;
#else
    return Vector3(x-rh.x, y-rh.y, z-rh.z);
#endif
}

Vector3 operator*(float s, const Vector3& v)
{
#if USE_YEPPP
    Vector3 ret;
    yepCore_Multiply_V32fS32f_V32f(&v.x, s, &ret.x , 3);
    return ret;
#else
    return Vector3(s*v.x,s*v.y,s*v.z);
#endif
}

I am using g++ compiler. Compiler options: g++ -Wall -fexceptions -fPIC -Wl,--no-as-needed -std=c++11 -pthread -ggdb Linker options: g++ -shared -lpthread -lyeppp -ldl

So any idea what am I doing wrong?

Answer 1

Yeppp! is optimized for processing arrays of 100+ elements.

It is not efficient on small arrays (like length-3 array in your example) due to limited ability to use SIMD and overheads of function call, dynamic dispatching, and parameter checks.