"#!/usr/bin/python3" only works if python3 is found in "/usr/bin".

Only minimal changes done so far (mostly print() stuff)

ELPA can now be linked against a 64bit integer version of MPI and
ScalaPack. This is an experimental feature

The following points are still to be done
- does not work with real QR-decomposition
- generalized routines return wrong results
- the C tests and the C Cannon algorithm implementation do not
  work (no 64bit header files for MPI *at least* with Intel MPI)

Obviously, recent versions of automake decided to filter out
an "test_" string which led to some surprises

and runs several elpas (still mpi-based) in parallel. Each elpa
"instance" then splits its communicator to row and column communicator,
as it is always done. This is actually often done in FHI-aims and was
previously leading to issues when using OmniPath. Hopefully was solved
by Intel MPI 2019.3. Keeping the test for future reference.

mpi_comm_parent is allways requred (it was not required before, but
actually the code internals expected it to be supplied, at least for
ELPA 2 calculation OR whenever GPU was used)

Pavel Kus authored Nov 09, 2018 and Pavel Kus committed Nov 15, 2018

and supplied to the elpa object by set methods

because otherwise the cannons algorithm is not usually tested

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

executables were generated event though the functionality is not present
in test.c

test.c currently does not support all the flags test.F90 does, so there
were a lot of useless test cases generated.

- per default only some tests are run
- by setting CHECK_LEVEL=extended all test jobs are run

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)

both fortran and C tests generated in generate_automake_test_programs.py
linker flags added by hand -- FIX this