- activated vectorization for LBM kernels

- renaming because of clashes with types.py from other packages

- first vectorization tests are running
- type system: use memoized getTypeOfExpression
- casts are done using sp.Function('cast')
- C backend adapted for vectorization support
- AST nodes can required optional headers

- support for kernels that run over walberla ghost layers

- old method produced unused variables
- old method was not deterministic in the output code i.e. ordering of
  the introduced constants
- moveConstantsBeforeLoops transformation was also not deterministic

-> reading from arrays was slower with some compilers

- pystencils can create now a non-compilable kernel that can be
  analyzed by kerncraft

- abstraction layer for selecting CUDA block and grid sizes
  - line based (was implemented before)
  - block based (new, more flexible)
-  new conditional (if/else) ast node, which is necessary for indexing schemes (guarding if)

- this extension is necessary for more generic boundary treatment
- cells can now be structs, i.e. contain different data types
- instead of having numeric index dimensions, one can use the index per cell to adress struct elements

- use data type class consistently instead of strings (in TypedSymbol, Field and jit module)
- new datatype class is based on numpy types with additional specifier information (const and restrict)
- translation between data type class and other modules (numpy, ctypes)

- due to unordered containers  the same method could produce different but functionally equivalent code
- this behaviour is bad for caching

-> switched to ordered containers

- check that fixed size kernels are called with arrays of the correct size
- checks that layout of compilation matches runtime layout
- not allowed any more to mix fixed & and variable sized fields in a kernel

Move my llvm demo notebook in the correct folder

and not as a string.
Changed name of the file TypedSymbol to types.
Fixed usage of dtype accordingly, however i might not have found every
usage of dtype.

- wrote a new, separate lattice model for cumulants
- tested with 2D LDC

problem in moveConstantBeforeLoops transformation:

--> a should end up here
{
for() {
  const int a = 5;
}
for() {
  const int a = 5
}
}

the "a" of the lower loop was not moved up, since it could not move across first loop (which is wrong)