DKRZ projects

• much expands C support of functionality previously only available in Fortran
• adds the distributed multi-array data structure especially to the C part
• full configure-time support for libtool
• minor fixes for various platforms and added support for BlueGene/Q

In summary the changes are:

• Better support for BlueGene/Q and cross-compilation.
• Copy constructors for xmaps and redists.
• Support for overlapping redist repeat constituents.
• Stricter declaration of some API functions (added const).
• 2 edge cases in stripe overlap got fixed.
• The tests got improved in numerous little places.
• Internal memory allocations have slightly less overhead.

The libaec repository, download page and everything else can now be found on our GlitLab server

https://gitlab.dkrz.de/k202009/libaec

Please update your links.

This release fixes the prevention of unnecessary duplication of MPI communicators from 0.4.2 to finally work in all cases.

This release contains a fix to prevent unnecessary duplication of MPI communicators.
Also, another example is added. It shows how to use yaxt for halo exchange of unstructured grid models.

This release contains minor fixes plus a switch to run configure tests with libtool so that users are no longer bothered with details of rpath and library dependencies.

• a minor optimization to prevent unneeded duplication MPI communicators,
• convenience functions to reduce user input at configure time
• further documentation on how to build on Cray XC systems
• various bug-fixes for compiler/MPI fail

The API is unchanged and this version, while a major step in regard to reliability, should be a drop-in replacement for everyone using 0.3.0 at this time.

This release significantly enhances the library:

• Fortran support is finalized, all public functions from the C API have a corresponding routine in the Fortran API.
• Performance has been improved for computations on large distributed objects while decreasing memory requirements at the same time.

Some highlights from this release:

• Performance improvement for encoding pre-precessed data.
• More efficient coding of second extension if reference sample is present.
• Ported library to Windows (Visual Studio).
• Supported building with CMake.
• Benchmarking target using ECHAM data (make bench)

• Improved computation of intersections for large index lists.
• Exposes more of the API to Fortran.
• Some performance/memory improvements.