[EPIC]: Optimize Segmented Scan

### 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.

As of https://github.com/NVIDIA/cccl/pull/6022, CUB provides device-level segmented scan primitive. The MVP assigns a single block per CTA, which leads to suboptimal performance.

### Describe the solution you'd like

This issue will track various optimizations that we have in mind for segmented scan.

### Describe alternatives you've considered

_No response_

### Additional context

_No response_