Add --target-cuda argument for selecting CUDA architecture

[vlad-perevezentsev]

This PR suggests adding --target-cuda argument to scripts/build_locally.py allowing to enable CUDA support and optionally specify the target architecture (e.g. sm_80).
If no architecture is specified, sm_50 is used by default.

$ python scripts/build_locally.py --target-cuda
# or
$ python scripts/build_locally.py --target-cuda=<arch>

The specified architecture is used to construct a SYCL alias target (e.g. nvidia_gpu_sm_80) and passed via -fsycl-targets option, following OneAPI for NVIDIA GPUs

• Have you provided a meaningful PR description?
• Have you added a test, reproducer or referred to an issue with a reproducer?
• Have you tested your changes locally for CPU and GPU devices?
• Have you made sure that new changes do not introduce compiler warnings?
• Have you checked performance impact of proposed changes?
• Have you added documentation for your changes, if necessary?
• Have you added your changes to the changelog?

[github-actions]

View rendered docs @ https://intelpython.github.io/dpnp/index.html

[antonwolfy]

It is not OFF by default now. Should this be updated?

Suggested change

	if (DPNP_TARGET_CUDA)
	if (NOT "x${DPNP_TARGET_CUDA}" STREQUAL "x")

[vlad-perevezentsev]

The empty string is False for this check if (DPNP_TARGET_CUDA)
I added this check in case when DPNP_TARGET_CUDA is passed as 0, OFF, NO, FALSE, N via cmake-opts argument

[antonwolfy]

in case when DPNP_TARGET_CUDA is passed as 0, OFF, NO, FALSE, N via cmake-opts argument

That is not the case when DPNP_TARGET_CUDA passed as an empty string. So it's still unclear for me.
Per my understanding the string can't be empty due to the check.

[vlad-perevezentsev]

You are right that --target-cuda= is checked in build_locally.py.
But if someone bypasses it via --cmake-opts="-DDPNP_TARGET_CUDA=" the empty string is still evaluated as FALSE in if(DPNP_TARGET_CUDA). Thus this condition safely handles both cases.
Using if (NOT "x${DPNP_TARGET_CUDA}" STREQUAL "x") would only check for non-empty strings but still treat values like OFF or 0 as TRUE

[antonwolfy]

Yes, it sounds reasonable.
But what is about similar flag for AMD build? Why don't we check the same there then?

[vlad-perevezentsev]

@antonwolfy it will be updated in the next PR.
Thank you

[github-actions]

Array API standard conformance tests for dpnp=0.19.0dev0=py312h509198e_23 ran successfully.
Passed: 1231
Failed: 0
Skipped: 9

[coveralls]

coverage: 71.705%. remained the same
when pulling 3cbcb31 on add_target_cuda
into e9e84fc on master.

[antonwolfy]

No more comments from me.
Thank you @vlad-perevezentsev