[FEA]: thrust::reduce needs no_sync version

[zcbenz]

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

Thrust

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

Existing thrust::reduce APIs all return the result in host, which means the call is always synchronous even when using par_nosync.

Describe the solution you'd like

There should be a version that takes a output iterator.

Describe alternatives you've considered

No response

Additional context

No response

[bernhardmgruber]

Thanks for raising awareness for this issue. We already track this as part of #4056.