如何加快我的双线性插值

我花了无数个小时试图加快我的双线性插值，但无济于事。我甚至尝试了SSE版本(双版本和浮动版本)，但它甚至比这个版本更慢。

有人有什么想法吗?

template <typename T>
__forceinline void interp2_mx(const T& x, const T& y,
                              const T* z,
                              const int32_t& n,
                              const int32_t& mm2,
                              const int32_t& nm2,
                              T& val,
                              const T& extrapval = T(0))
{
    int64_t xp = (int64_t)(x) - 1;      // adjust for MATLAB indexing
    int64_t yp = (int64_t)(y) - 1;
    if (xp < 0 || xp > nm2 || yp < 0 || yp > mm2)
    {
        val = extrapval;
    }
    else
    {
        const T* line = z + yp * n + xp;
        T xf = x - (int64_t)(x);        
        T yf = y - (int64_t)(y);
        T x1mf = (T)1 - xf;
        T y1mf = (T)1 - yf;
        T v00 = x1mf * y1mf * (*(line));
        T v01 = xf * y1mf * (*(line + 1));     
        T v10 = x1mf * yf * (*(line + n));     
        T v11 = xf * yf * (*(line + n + 1));   
        val = v00 + v01 + v10 + v11;
    }
} 
template <typename T>
void interp2(const T* z,
             const int32_t& mz, const int32_t& nz,
             const T* xi, const T* yi,
             const int32_t& mi, const int32_t& ni,
             T* zi,
             const T& extrapval = T(0))
{
    const int32_t nzm2 = nz - 2;
    const int32_t mzm2 = mz - 2;    
    #pragma omp parallel for
    for (int m = 0; m < mi; ++m)
    {        
        T* line_zi = zi + m * ni;    
        const T* x = xi + m * ni;
        const T* y = yi + m * ni;
        for (int n = 0; n < ni; ++n, ++x, ++y, ++line_zi)
        {
            interp2_mx((*x), (*y), z, nz, mzm2, nzm2, (*line_zi));            
        }
    }
}