Reimplementing CUDA parallel reduction with template operations.

src/core/cuda/reduction-operations.h

src/implementation/core/CMakeLists.txt

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

src/implementation/core/cuda/CMakeLists.txt

src/implementation/core/cuda/reduction-operations_impl.cu

src/implementation/core/cuda/reduction-operations_impl.h

src/implementation/core/memory-operations.h

tests/unit-tests/CMakeLists.txt

tests/unit-tests/core/cuda/CMakeLists.txt

tests/unit-tests/core/cuda/reduction-test.cu

tests/unit-tests/core/cuda/tnlCudaMemoryOperationsTester.h

tests/unit-tests/core/cuda/tnlCudaReductionTester.h