[FEA]: Introduce combinational ranges into cuda.parallel

[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

General CCCL

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

We are lacking combinational ranges, such as thrust::transform_{input,output}_iterator, thrust::zip_iterator, and cub::CacheModified{Input,Output}Iterator in cuda.parallel.

Describe the solution you'd like

Design and implement combinational ranges for cuda.parallel.experimental.itertools. We might consider map(python_function, iterable) for thrust::transform_{input,output}_iterator, zip(rng1, rng2, ...) for thrust::zip_iterator, and cache(modifier, iterable) where modifier is from

cccl/cub/cub/thread/thread_load.cuh

Lines 60 to 69 in 0e09815

	enum CacheLoadModifier
	{
	LOAD_DEFAULT, ///< Default (no modifier)
	LOAD_CA, ///< Cache at all levels
	LOAD_CG, ///< Cache at global level
	LOAD_CS, ///< Cache streaming (likely to be accessed once)
	LOAD_CV, ///< Cache as volatile (including cached system lines)
	LOAD_LDG, ///< Cache as texture
	LOAD_VOLATILE, ///< Volatile (any memory space)
	};

Describe alternatives you've considered

No response

Additional context

No response

[gevtushenko]

#2788 introduced transform and cache modified iterators. Will track zip and transform output iterator in a different issue.