Adding parallel sort

CMakeLists.txt

src/CMakeLists.txt

src/Graph/map_graph.hpp

src/Grid/cuda/cuda_grid_gpu_funcs.cuh

src/Grid/cuda/map_grid_cuda_ker.cuh

src/NN/CellList/CellList_gpu_test.cu

src/NN/CellList/cuda/CellList_gpu.hpp

src/Vector/cuda/map_vector_sparse_cuda_ker.cuh

src/Vector/cuda/map_vector_sparse_cuda_ker_unit_tests.cu

src/Vector/performance/vector_performance_test.hpp

src/memory_ly/memory_c.hpp

src/performance.hpp

src/timer.hpp

src/util/cuda/scan_ofp.cuh

src/util/cuda/scan_sort_cuda_unit_tests.cu

src/util/cuda/sort_ofp.cuh