Merge branch 'InplaceGpuBenchmark' into 'master'

...hmarks/FlowAroundSphereCodeGen/FlowAroundSphereCodeGen.py

apps/benchmarks/UniformGridGPU/CMakeLists.txt

apps/benchmarks/UniformGridGPU/UniformGridGPU.cpp

apps/benchmarks/UniformGridGPU/UniformGridGPU.py

apps/benchmarks/UniformGridGPU/UniformGridGPU_AA.cpp

apps/benchmarks/UniformGridGPU/old_ideas/UniformGridGPU.cpp

apps/benchmarks/UniformGridGPU/old_ideas/UniformGridGPU.prm

apps/benchmarks/UniformGridGPU/old_ideas/UniformGridGPU.py

...s/UniformGridGPU/old_ideas/UniformGridGPU_Communication.h

...rmGridGPU/old_ideas/simulation_setup/benchmark_configs.py

...UniformGridGPU/old_ideas/simulation_setup/single_node.prm

apps/benchmarks/UniformGridGPU/roofline_model/roofline.ods

...arks/UniformGridGPU/simulation_setup/benchmark_configs.py

python/pystencils_walberla/utility.py

src/cuda/CMakeLists.txt

src/cuda/lbm/CombinedInPlaceGpuPackInfo.h

src/field/Field.h

src/field/Field.impl.h

src/lbm/all.h

src/lbm/inplace_streaming/TimestepTracker.h