[FEA]: Evaluate performance impact of graph capturable segmented sort

### 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

CUB

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

We have to evaluate performance for https://github.com/NVIDIA/cccl/issues/10799.

### Describe the solution you'd like

This issue can be closed with nvbench compare result run on upstream device segmented sort vs graph capturable device segmented sort from https://github.com/NVIDIA/cccl/issues/10799 on B200 and 6000 Pro.

### Describe alternatives you've considered

_No response_

### Additional context

_No response_