Add support of dpnp.less_equal()

[antonwolfy]

The PR introduces a support of dpnp.less_equal() function in dpnp.
It includes core implementation which will be reused later while adding other comparison functions.

This PR is fixing issue reported in #1251.

• Have you provided a meaningful PR description?
• Have you added a test, reproducer or referred to 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?
• If this PR is a work in progress, are you filing the PR as a draft?

[oleksandr-pavlyk]

A validation step is missing:

In [24]: x = dpnp.random.randn(10)

In [25]: x2 = dpnp.random.rand(12)

In [26]: (x <= x2)._array_obj
Out[26]: usm_ndarray(True)

In [27]: (x <= x2)
Out[27]: <dpnp.dpnp_array.dpnp_array at 0x7feefa759760>

In [28]: import numpy as np

In [29]: x, x2 = np.random.randn(10), np.random.randn(12)

In [30]: x <= x2
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [30], in <cell line: 1>()
----> 1 x <= x2

ValueError: operands could not be broadcast together with shapes (10,) (12,)

[antonwolfy]

A validation step is missing:

In [24]: x = dpnp.random.randn(10)

In [25]: x2 = dpnp.random.rand(12)

In [26]: (x <= x2)._array_obj
Out[26]: usm_ndarray(True)

In [27]: (x <= x2)
Out[27]: <dpnp.dpnp_array.dpnp_array at 0x7feefa759760>

In [28]: import numpy as np

In [29]: x, x2 = np.random.randn(10), np.random.randn(12)

In [30]: x <= x2
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [30], in <cell line: 1>()
----> 1 x <= x2

ValueError: operands could not be broadcast together with shapes (10,) (12,)

Thank you for the shared finding. The issue is fixed in new commit (more tests added to cover the use case).