Merge branch 'feature/no-mpi-option' into 'master'

ref:extensions/dune-codegen Useful for performance measuring with Intel SDE.

See merge request [extensions/dune-codegen!334]

  [extensions/dune-codegen!334]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/334

Merge branch 'feature/fix-blockstructured-alias' into 'master'

See merge request [extensions/dune-codegen!339]

  [extensions/dune-codegen!339]: Noneextensions/dune-codegen/merge_requests/339

Merge branch 'feature/automatically-add-pthread' into 'master'

ref:extensions/dune-codegen this need cmake 3.1, if the cmake version should
stay at 2.8 I could find another way to link it.

fixes [#153]

See merge request [extensions/dune-codegen!337]

  [#153]: gitlab.dune-project.org/NoneNone/issues/153
  [extensions/dune-codegen!337]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/337


Closes #153

Merge branch 'feature/block-preconditioner' into 'master'

ref:extensions/dune-codegen Allows the symbolic extraction of the block
diagonal of a DG operator as well as the (rank 1) point diagonal of that
blockdiagonal. Sum factorized matrixfree evaluation of both of these is
implemented.

See merge request [extensions/dune-codegen!332]

  [extensions/dune-codegen!332]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/332

this need cmake 3.1, if the cmake version should stay at 2.8 I could
find another way to link it

Merge branch 'feature/show-options-entrypoint' into 'master'

See merge request [extensions/dune-codegen!330]

  [extensions/dune-codegen!330]: Noneextensions/dune-codegen/merge_requests/330

Merge branch 'feature/already-consistent-grid-option' into 'master'

ref:extensions/dune-codegen Useful to reduce overhead when doing performance
measuring.

See merge request [extensions/dune-codegen!333]

  [extensions/dune-codegen!333]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/333

Merge branch 'feature/fix-typo' into 'master'

See merge request [extensions/dune-codegen!336]

  [extensions/dune-codegen!336]: Noneextensions/dune-codegen/merge_requests/336

Merge branch 'feature/cache-basis-in-constructor-blockstructured' into 'master'

See merge request [extensions/dune-codegen!335]

  [extensions/dune-codegen!335]: Noneextensions/dune-codegen/merge_requests/335

Merge branch 'feature/blockstructured-remove-clutter' into 'master'

See merge request [extensions/dune-codegen!323]

  [extensions/dune-codegen!323]: Noneextensions/dune-codegen/merge_requests/323

The Exadune preconditioners cant handle one sided assembly for reasons.

Merge branch 'feature/fenicsesque-finite-elements' into 'master'

ref:extensions/dune-codegen TODOs:

-   [x] Register all finite elements from PDELab into UFL
-   [ ] Adapt driver generation so that they are actually used
-   [ ] Adapt examples to be more precise about the basis they are using

See merge request [extensions/dune-codegen!322]

  [extensions/dune-codegen!322]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/322

Merge branch 'feature/sumfact-loop-reordering' into 'master'

ref:extensions/dune-codegen Performance transformation through loop nest
reordering. There are two ways to reorder loops in a tensor contraction:

1.  Directly accumulate in output variable after setting to zero
2.  Accumulating in a large enough temporary

This merge request implements these ways of loop reordering and the
possibility to create an autotune target directly from the loopy kernel.

See merge request [extensions/dune-codegen!305]

  [extensions/dune-codegen!305]: gitlab.dune-project.org/extensions/dune-codegen/merge_requests/305

Run the function call over multiple data sets.

Replace placeholders in template file with actual code. This makes it a lot
easier to restructure the benchmark.

This rewrite was necessary for the cases where the instruction contains a
reduction but the expression itself is not a reduction. Besides fixing this bug
it greatly reduces code duplication and increases code quality.

This just reverts to the old behaviour. The new implementation of loop
reordering doesn't need that anymore.