Added CUDA benchmarks

pystencils_benchmark/__init__.py

pystencils_benchmark/benchmark.py

pystencils_benchmark/benchmark_gpu.py

pystencils_benchmark/enums.py

pystencils_benchmark/templates/NVCC.mk

pystencils_benchmark/templates/cpu/kernel.c

pystencils_benchmark/templates/cpu/kernel.h

pystencils_benchmark/templates/cpu/main.c

pystencils_benchmark/templates/gpu/kernel.cu

pystencils_benchmark/templates/gpu/kernel.h

pystencils_benchmark/templates/gpu/main.c

tests/test_benchmark.py