GitLab

on selected mpi ranks using suppress_warnings option

avoiding calling both check eigenvalues AND check eigenvalues and
eigenvectors for analytic eigenvector test

if provided a a fourth parameter, all correctness checks will be
skipped. Can be usefull for repeated performance tests.

instead, blacs context has to be set beforehand

added possibility to re-use the already decomposed matrix B in the
generalized problem
Added respective test

* tested with elpa1 only (should be sufficient)
* not using Hermitian multiply at the moment
* requires scalapack

and some modifications in test.f90

This test was wrong, it was computing A * A^T instead of A^T * A.
The latter is correct since our implementation of Cholesky decomposition
stores the triangular matrix in the upper triangle
The test was passing only because the Cholesky decomposition was tested
with diagonal matrix only, than this does not matter.

To be used like this

   class(elpa_t), pointer      :: e
   class(elpa_autotune_t), pointer :: tune_state

   e => elpa_allocate()
   call e%set(...)
   [...]
   assert_elpa_ok(e%setup())

   tune_state => e%autotune_setup(ELPA_AUTOTUNE_FAST, ELPA_AUTOTUNE_DOMAIN_REAL)

   ! Autotuning loop, continues until all combinations have been tried
   do while (e%autotune_step(tune_state))
     ! Do the steps that are representative of your calculation
     call e%eigenvectors(a, ev, z, error)
   end do

   ! Fix best parameters, and de-allocate the autotune object
   call e%autotune_set_best(tune_state)
   call elpa_autotune_deallocate(tune_state)

in Fortran test.F90

But allow this in cholesky and hermitian multiply test

It is planned to add another matrix type for the tests.
The names of the prepare routines have become a bit inconsistent and
confusing. Thus the rename

unlike elpa 2stage, scalapack computes only part of eigenvalues
if only part of eigenvectors are required. Check only those.

unlike elpa 2stage, scalapack computes only part of eigenvalues
if only part of eigenvectors are required. Check only those.

with obvious meaning

for easier comparisons of elpa and mkl, a test case using scalapack
function pdsyevd has been added