Include CUDA stack information in profile plots

We're in the process of include low-level (e.g., C calls) profiling plots in https://github.com/dask/distributed/pull/2575. After that it may be useful to do the same with CUDA, we could add both host-side calls (e.g., memory allocation) and kernel calls.

This can be done with the help of [CUPTI - CUDA Profiling Tools Interface](https://docs.nvidia.com/cuda/cupti/index.html). Perhaps the C side could (and maybe, should) be part of a small library decoupled from this repository, just like https://github.com/numba/stacktrace.