Add support for rank-n tensors to tilize and untilize

[jaykru-tt]

Ticket

#15165

What's changed

• Adds support for rank-n tensors to the tilize and untilize ops. In particular this introduces support for 5D tensors.
• We support rank-n tensors by first squeezing to a supported rank <= 4, then performing the tilize/untilize, then unsqueezing back to the original shape/rank.
• Adds tests for a handful of 5D cases to both the untilize and tilize unit test suites.

Checklist

• Post commit CI passes
• Model regression CI testing passes
• Device performance regression CI testing passes
• New/Existing tests provide coverage for changes

[github-actions]

⚠️ Clang-Tidy found issue(s) with the introduced code (1/1)

[github-actions]

⚠️ Clang-Tidy found issue(s) with the introduced code (1/1)

[github-actions]

⚠️ performance-unnecessary-value-param ⚠️
parameter base_untilize is passed by value and only copied once; consider moving it to avoid unnecessary copies

Suggested change

	.operation = std::move(base_untilize)});
	.operation = std::move(base_untilize)});

[github-actions]

⚠️ performance-unnecessary-value-param ⚠️
parameter base_tilize is passed by value and only copied once; consider moving it to avoid unnecessary copies

Suggested change

	.operation = std::move(base_tilize)});
	.operation = std::move(base_tilize)});

[jaykru-tt]

I messed up a few of the tilize tests with an unnecessary refactor. Re-running post-commit to be safe then should be able to merge.