Add cudf::strings::contains_multiple

[davidwendt]

Description

Add new cudf::strings::contains_multiple API to search multiple targets within a strings column.
Output is a table where the number of columns is the number of targets and each row is a boolean indicating that target was found at the row or not.
This PR is to help in collaboration with #16641

Checklist

• I am familiar with the Contributing Guidelines.
• New or existing tests cover these changes.
• The documentation is up to date with these changes.

[res-life]

This PR has better performance compared to the previous PR.
Below is nsys info and end to end time:

previous PR:

Time  Total Time  Instances Avg Med Min Max StdDev  Name
27.0%	19.388 s	792	24.480 ms	18.258 ms	2.157 ms	79.471 ms	22.218 ms	cudf::strings::detail::<unnamed>::multi_contains_warp_parallel_multi_scalars_fn(cudf::column_device_view, cudf::column_device_view, cudf::device_span<char, (unsigned long)18446744073709551615>, cudf::column_device_view, cudf::device_span<bool *, (unsigned long)18446744073709551615>)

End to End time is: 53s

this PR

Time	Total Time	Instances	Avg	Med	Min	Max	StdDev	Name
16.9%	11.033 s	528	20.896 ms	14.290 ms	1.808 ms	63.529 ms	18.714 ms	void cudf::strings::detail::<unnamed>::multi_contains_kernel<(long)32>(cudf::column_device_view, cudf::column_device_view, const unsigned char *, const int *, const int *, int, bool *, cudf::device_span<bool *, (unsigned long)18446744073709551615>)

End to End time is: 46s

[mythrocks]

Sorry for the delay. It took a while to get my head around it. Thank you, this is an impressive speedup.

[res-life]

@davidwendt Other PRs are depending on this, could you merge this PR?

[davidwendt]

/merge

[davidwendt]

/merge

[res-life]

/merge

[kingcrimsontianyu]

Lgtm. Thanks!

[bdice]

I will apply one small docstring fix I saw while reviewing C++, then I can approve the CMake (I didn't want to approve yet because it would auto-merge since /merge has already been added).