This commit is contained in:
Jitse Niesen 2010-04-02 21:33:34 +01:00
commit d88d1cfa62
2 changed files with 9 additions and 10 deletions

View File

@ -369,10 +369,14 @@ static EIGEN_DONT_INLINE EIGEN_UNUSED Packet4f ei_pcos(Packet4f x)
// For detail see here: http://www.beyond3d.com/content/articles/8/
static EIGEN_UNUSED Packet4f ei_psqrt(Packet4f _x)
{
Packet4f half = ei_pmul(_x, ei_pset1(.5f));
Packet4f x = _mm_rsqrt_ps(_x);
x = ei_pmul(x, ei_psub(ei_pset1(1.5f), ei_pmul(half, ei_pmul(x,x))));
return ei_pmul(_x,x);
Packet4f half = ei_pmul(_x, ei_pset1(.5f));
/* select only the inverse sqrt of non-zero inputs */
Packet4f non_zero_mask = _mm_cmpgt_ps(_x, ei_pset1(std::numeric_limits<float>::epsilon()));
Packet4f x = _mm_and_ps(non_zero_mask, _mm_rsqrt_ps(_x));
x = ei_pmul(x, ei_psub(ei_pset1(1.5f), ei_pmul(half, ei_pmul(x,x))));
return ei_pmul(_x,x);
}
#endif // EIGEN_MATH_FUNCTIONS_SSE_H

View File

@ -131,17 +131,12 @@ void RealSchur<MatrixType>::hqr2()
Scalar exshift = 0.0;
Scalar p=0,q=0,r=0,s=0,z=0,w,x,y;
// Store roots isolated by balanc and compute matrix norm
// Compute matrix norm
// FIXME to be efficient the following would requires a triangular reduxion code
// Scalar norm = m_matT.upper().cwiseAbs().sum() + m_matT.corner(BottomLeft,n,n).diagonal().cwiseAbs().sum();
Scalar norm = 0.0;
for (int j = 0; j < size; ++j)
{
// FIXME what's the purpose of the following since the condition is always false
if ((j < low) || (j > high))
{
m_eivalues.coeffRef(j) = ComplexScalar(m_matT.coeff(j,j), 0.0);
}
norm += m_matT.row(j).segment(std::max(j-1,0), size-std::max(j-1,0)).cwiseAbs().sum();
}