[FEA]: List available mangled benchmark names

### Is this a duplicate?

- [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md)

### Area

General CCCL

### Is your feature request related to a problem? Please describe.

Benchmarking script produces the following output:
```
&&&& RUNNING bench
&&&& PERF cub_bench_adjacent_difference_subtract_left_base_T_ct__I32___OffsetT_ct__I32___Elements_io__pow2__28 0.002529280027374625 -sec
&&&& PERF cub_bench_adjacent_difference_subtract_left_base_T_ct__I32___OffsetT_ct__I64___Elements_io__pow2__28 0.0025313280057162046 -sec
```
Without running the full test suite, the full list of mangled names is not available. It's also not immediately obvious how to turn this name into a command line for benchmarking given workload.

### Describe the solution you'd like

Adding command line argument to `run.py` that lists all mangled names along with command line to launch it would help QA.

### Describe alternatives you've considered

_No response_

### Additional context

_No response_