Recetnly, i was trying to replace the function for matrix inverse by that of MKL. However, after making it, i found that the time used for computing was not improved and be slower. I don't know the real reason.It could be appreciated that anyone can help me.
The original subroutine was syminvg.
SUBROUTINE syminvg(n,q,norm,nsing,parflg,sbrName,bigajj_limit,utest)
! -------------------------------------------------------------------------
! Purpose: Inversion symm. matrix with pivot search on the diagonal.
! Algorithm acm 150, H. Rutishauser 1963
! Change: upper triangle of matrix in vektor q(n*(n+1)/2)
!
! Author: H. Rutishauser, C. Urschl
!
! Created: 24-Jan-2003
!
! Changes: 09-Aug-2010 RD: Generic use, only one version for all purposes
! 27-Oct-2010 SL: use m_bern with ONLY
! 23-May-2011 RD: Special handling for diagonal elements with NaN
! 30-Jul-2012 RD: Evaluate the inversion (only for GRP_AIUB)
! 22-Sep-2012 RD: Change variable name "unit" to "utest"
!
! Copyright: Astronomical Institute
! University of Bern
! Switzerland
! -------------------------------------------------------------------------
I used two subroutines of intel mkl:
CALL DPPTRF('U',n,q0,INFO) CALL DPPTRI('U',n,q0,INFO)