>>> import time
>>> start_gpu = cp.cuda.Event()
>>> end_gpu = cp.cuda.Event()
>>>
>>> start_gpu.record()
>>> start_cpu = time.perf_counter()
>>> out = my_func(a)
>>> end_cpu = time.perf_counter()
>>> end_gpu.record()
>>> end_gpu.synchronize()
>>> t_gpu = cp.cuda.get_elapsed_time(start_gpu, end_gpu)
>>> t_cpu = end_cpu - start_cpu