[FEA]: Block-level `TransformReduce`

### 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.

#1091 added a new CUB device-algorithm for transform reduce, to exploit potential opportunity in vectorized loads As a user, I expect to see a similar API at the block-level, potentially allowing register saving + other benefits that are also provided by the device transform reduce.

### Describe the solution you'd like

`cub::BlockReduce::TransformReduce`

### Describe alternatives you've considered

_No response_

### Additional context

_No response_