- 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)

Michael Kuron authored 8 years ago and Martin Bauer committed 8 years ago

This commit makes the Python code backwards compatible down to Python 2.7. Previously it would only run on Python 3.5 and up.

Problems fixed included:
- `time.perf_counter()` doesn't exist
- all classes need to be new-style
- `functools.lru_cache` doesn't exist
- only the last argument to a function call can be `*`-expanded
- the `nonlocal` keyword doesn't exist
- metaclasses are used with a different syntax
- `yield from` doesn't exist
- `tempdir.TemporaryDirectory` doesn't exist
- iterators need a `next()` method

- 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

Although expressions have args and function as a tree, args cannot be
modified. So tree-transformations are not possible.
Sympy has subs function, however it replaces all matched in any
subexpression, of the expression (i.e. not only in args but in args args
and so on).

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.

- new waLBerla only benchmark

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)

- LoopOverDomain changed to be able to loop over rectangular sub-region of field
- support for slicing with makeSlice

- added sphinx files for documentation generation
- collected kernel creation functions in new "cpu" and "cudagpu" modules