[FEA]: Implement cuda.parallel.segmented_reduce algorithm

[gevtushenko]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this request and that I agree to the Code of Conduct

Area

Not sure

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

We need a cuda.parallel version of the cub::DeviceSegmentedReduce algorithm.

Describe the solution you'd like

Asynchronous cuda.parallel.segmented_reduce_into algorithm.

Describe alternatives you've considered

No response

Additional context

No response

[oleksandr-pavlyk]

@gevtushenko @shwina With all four sub-tasks complete, should this issue be resolved? Or is there more work to be done?

[leofang]

All is good! Thanks a lot, Sasha!