- small (length < 5) arrays with shape and stride information had to be
  memcpy'd to the GPU before every kernel call
- instead of passing the information as arrays, the single elements are
  passed
- leads to more function arguments, but simplifies GPU kernel calls

-> changes in all backends required

- bugfix in vector-typing of piecewise functions
- cast_function is now a sympy atom - fixes problems with sympy > 1.1
- replace_inner_stride_with_one is a bit faster now

- support aligned load/stores
- nontemporal stores
- aligned memory allocation for arrays and temporary buffers

- vectorization for loops with ranges that are not a multiple of vector width
- vectorization for variable sized loops if special transformation
  replace_inner_stride_with_one is run

- flags can be force when setting boundaries, this is helpful for:
- setting up quantities (e.g. relaxation rate..) dependent on current
  flag configuration
- bit operation fix when pickling: function has to have the same name
  as the python object

- test run again
- notebooks not yet

- single function to create kernel for specified target
- data type creation from string - reuse numpy functionality
- bugfixes in dot display

- alignment of index array when using additional data
- data types have been hashed incorrectly

- support for logical operators, and/or
- both phase field kernels can be vectorized now

- phasefield phi sweep vectorizes successfully

Added LLVM: CodePrinter and a compiler
Updated data_types
Added tests
Added jupyter notebooks
Fixed bugs
Restructured transformation functions

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

- sympys piecewise defined functions are mapped to blend instructions
- cast function is now a class
- several bugfixes

- 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

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

- 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)

- windows support
- automatic caching and creation of shared library with all generated kernels
- restrict keyword and function prefixes are preprocessor macros now -> easier to generate one code for linux, cuda, windows