- counter-based philox RNG: counter/key is filled with cell coordinate
  and optional external parameters like block position and time step
- works on CPU and GPU - on CPU only for non-vectorized versions

- introduced more flexible "CustomCodeNode" that can inject
  backend-specific hand-written code

- 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

- updates in lbmpy benchmark
-> enables better numa placement

- removed warnings
- added flake8 as CI target

- test run again
- notebooks not yet

- assignment collection
- sympyextensions

Modified the gitlab-ci for benchmarking purposes
Created a new Dockerfile for benchmarking purposes, which includes the
intel compiler.
Docker file now has likwid installed as well.
Created a machine file for the benchmarking machine.
Kerncraft updated and fixed.

TODOs:
    - cleanup of the yaml files
    - Test the Skylake machine file and kerncraft_coupling for correct
      behaviour

Updated testing of kerncraft_coupling and some functions in
kerncraft_coupling in order to be compatible with the kerncraft version 5.1