Setting a bandwdith of the input matrix via

elpa%set("bandwidth",bw)

tells ELPA 2stage, that matrix is already a banded matrix
with bandwidth bw. Then some compute steps can be skipped

The legacy API is has been (internally) ported to use the new interface.
The intent is that users of the legacy API do not have to change their
codes.

Next step is to completely adapt the .gitlab-ci.yml file

Still missing is the compatibility layer, currently it only compiles
when configure is called with

  --disable-legacy

Also, a more general solution to parameter passing via environment
variables would be nice.

There are also at least those files, where stops without 1 are present

src/elpa1/legacy_interface/elpa_cholesky_template_legacy.X90:
src/elpa1/legacy_interface/elpa_invert_trm_legacy.X90:
src/elpa1/legacy_interface/elpa_multiply_a_b_legacy.X90:
src/elpa1/legacy_interface/elpa_solve_tridi_legacy.X90:

should they be also changed?

Actually, the complex cases have not been checked so far.
Furthermore, there has been an inconsistency between setting

set("gpu",1)

and *NOT* setting a GPU kernel via the set mechanism. Then, the
default kernel (which is *NOT* GPU) has been used

Unfortunately C macros can have only 1 line and length of line is
limited ---> workaround to be able to compile

They are in a sad state, it's all copy&paste and chaos. This commit
only touches the surface so far.

This attempt at a new, more flexible API for ELPA should hopefully
result in less ABI/API breaking changes in the future.

The new API features a generic key/value system for options that can be
extended without changing any exported symbols or function signatures,
so that new, optional features do not influence existing usage of ELPA.

We hope this makes life easier for users of ELPA - at least in the long
run when they migrated to this newest of ABI changes :)

Example usage (explicit documentation to be done in a future commit):

   if (elpa_init(20170403) /= ELPA_OK) then
     error stop "ELPA API version not supported"
   endif

   e = elpa_create(na, nev, na_rows, na_cols, nblk, mpi_comm_world, my_prow, my_pcol, success)

   call e%set("solver", ELPA_SOLVER_2STAGE)
   call e%set("real_kernel", ELPA_2STAGE_REAL_GENERIC)

   call e%solve(a, ev, z, success)

   call e%destroy()

   call elpa_uninit()