Refactoring the reduction on the CUDA device.

buildAll

src/CMakeLists.txt

src/config/CMakeLists.txt

src/core/cuda/CMakeLists.txt

src/core/cuda/cuda-reduction.h

src/core/cuda/reduction-operations.h

src/core/cuda/reduction.h

src/implementation/CMakeLists.txt

src/implementation/core/CMakeLists.txt

src/implementation/core/cuda-long-vector-kernels.h

src/implementation/core/cuda/CMakeLists.txt

src/implementation/core/cuda/cuda-reduction_impl.cpp

src/implementation/core/cuda/cuda-reduction_impl.cu

src/implementation/core/cuda/cuda-reduction_impl.h

src/implementation/core/cuda/reduction_impl.h

src/implementation/core/memory-operations.h

src/implementation/core/memory-operations_impl.cpp

src/implementation/core/memory-operations_impl.cu

src/implementation/core/vector-operations.h

src/solvers/ode/tnlMersonSolver.h