Merge branch 'master' into update_tests

Author: vtavana

.pre-commit-config.yaml

@@ -34,7 +34,8 @@ repos:
             (?x)^(
                 dpnp/tests/test_arraycreation.py|
                 dpnp/tests/test_sycl_queue.py|
-                dpnp/tests/test_usm_type.py
+                dpnp/tests/test_usm_type.py|
+                dpnp/tests/third_party/cupy/core_tests/test_nep50_examples.py
             )$
     -   id: python-no-log-warn
     -   id: python-use-type-annotations

CHANGELOG.md

@@ -13,6 +13,26 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Fixed
 
 
+## [0.16.1] - 12/06/2024
+
+This is a bug-fix release.
+
+### Changed
+
+* Changed to use `Miniforge` installer in GitHub actions [#2057](https://github.com/IntelPython/dpnp/pull/2057)
+* Updated `README.md` to reflect current installation requirements and available options [#2166](https://github.com/IntelPython/dpnp/pull/2166)
+* Corrected the list of owners and code maintainers [#2185](https://github.com/IntelPython/dpnp/pull/2185)
+* Bumped the version of `oneMKL` interface used in dpnp build by default to align it with `2025.0` oneAPI release [#2193](https://github.com/IntelPython/dpnp/pull/2193)
+
+### Fixed
+
+* Resolved an issue with Compute Follows Data inconsistency in `dpnp.extract` function [#2172](https://github.com/IntelPython/dpnp/pull/2172)
+* Resolved an import error when using `dpnp` in virtual environment on Linux [#2199](https://github.com/IntelPython/dpnp/pull/2199)
+* Fixed incorrect result produced by `dpnp.fft.fft` function when input array has negative strides [#2202](https://github.com/IntelPython/dpnp/pull/2202)
+* Fixed an issue with `numpy.ndarray` input processing in the `dpnp.from_dlpack` function and updated the documentation [#2209](https://github.com/IntelPython/dpnp/pull/2209)
+* Resolved a compilation error when building with DPC++ 2025.1 compiler [#2211](https://github.com/IntelPython/dpnp/pull/2211)
+
+
 ## [0.16.0] - 10/14/2024
 
 This release reaches an important milestone by making offloading fully asynchronous. Calls to `dpnp` submit tasks for execution to DPC++ runtime and return without waiting for execution of these tasks to finish. The sequential semantics a user comes to expect from execution of Python script is preserved though.

doc/conf.py

@@ -220,6 +220,7 @@ def _can_document_member(member, *args, **kwargs):
     "python": ("https://docs.python.org/3/", None),
     "numpy": ("https://docs.scipy.org/doc/numpy/", None),
     "scipy": ("https://docs.scipy.org/doc/scipy/reference/", None),
+    "dpctl": ("https://intelpython.github.io/dpctl/latest/", None),
 }
 
 # If true, `todo` and `todoList` produce output, else they produce nothing.

dpnp/__init__.py

@@ -49,6 +49,9 @@
         [os.getenv("PATH", ""), mypath, dpctlpath]
     )
 
+# Borrowed from DPCTL
+from dpctl.tensor import DLDeviceType
+
 from dpnp.dpnp_array import dpnp_array as ndarray
 from dpnp.dpnp_flatiter import flatiter as flatiter
 from dpnp.dpnp_iface_types import *

dpnp/backend/kernels/dpnp_krnl_common.cpp

@@ -35,11 +35,23 @@
 #include "queue_sycl.hpp"
 #include <dpnp_iface.hpp>
 
+/**
+ * Version of SYCL DPC++ 2025.1 compiler where support of
+ * sycl::ext::oneapi::experimental::properties was added.
+ */
+#ifndef __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT
+#define __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT 20241129
+#endif
+
 namespace mkl_blas = oneapi::mkl::blas;
 namespace mkl_blas_cm = oneapi::mkl::blas::column_major;
 namespace mkl_blas_rm = oneapi::mkl::blas::row_major;
 namespace mkl_lapack = oneapi::mkl::lapack;
 
+#if __SYCL_COMPILER_VERSION >= __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT
+namespace syclex = sycl::ext::oneapi::experimental;
+#endif
+
 template <typename _KernelNameSpecialization1,
           typename _KernelNameSpecialization2,
           typename _KernelNameSpecialization3>
@@ -78,8 +90,13 @@ sycl::event dot(sycl::queue &queue,
             cgh.parallel_for(
                 sycl::range<1>{size},
                 sycl::reduction(
-                    result_out, std::plus<_DataType_output>(),
-                    sycl::property::reduction::initialize_to_identity{}),
+                    result_out, sycl::plus<_DataType_output>(),
+#if __SYCL_COMPILER_VERSION >= __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT
+                    syclex::properties(syclex::initialize_to_identity)
+#else
+                    sycl::property::reduction::initialize_to_identity {}
+#endif
+                        ),
                 [=](sycl::id<1> idx, auto &sum) {
                     sum += static_cast<_DataType_output>(
                                input1_in[idx * input1_strides]) *

dpnp/dpnp_array.py

@@ -150,7 +150,7 @@ def mT(self):
         if self.ndim < 2:
             raise ValueError("matrix transpose with ndim < 2 is undefined")
 
-        return self._array_obj.mT
+        return dpnp_array._create_from_usm_ndarray(self._array_obj.mT)
 
     def to_device(self, target_device):
         """Transfer array to target device."""

dpnp/dpnp_iface.py

@@ -62,7 +62,6 @@
     "check_limitations",
     "check_supported_arrays_type",
     "default_float_type",
-    "from_dlpack",
     "get_dpnp_descriptor",
     "get_include",
     "get_normalized_queue_device",
@@ -443,60 +442,6 @@ def default_float_type(device=None, sycl_queue=None):
     return map_dtype_to_device(float64, _sycl_queue.sycl_device)
 
 
-def from_dlpack(obj, /, *, device=None, copy=None):
-    """
-    Create a dpnp array from a Python object implementing the ``__dlpack__``
-    protocol.
-
-    See https://dmlc.github.io/dlpack/latest/ for more details.
-
-    Parameters
-    ----------
-    obj : object
-        A Python object representing an array that implements the ``__dlpack__``
-        and ``__dlpack_device__`` methods.
-    device : {:class:`dpctl.SyclDevice`, :class:`dpctl.SyclQueue`,
-              :class:`dpctl.tensor.Device`, tuple, None}, optional
-        Array API concept of a device where the output array is to be placed.
-        ``device`` can be ``None``, an oneAPI filter selector string,
-        an instance of :class:`dpctl.SyclDevice` corresponding to
-        a non-partitioned SYCL device, an instance of :class:`dpctl.SyclQueue`,
-        a :class:`dpctl.tensor.Device` object returned by
-        :attr:`dpctl.tensor.usm_ndarray.device`, or a 2-tuple matching
-        the format of the output of the ``__dlpack_device__`` method,
-        an integer enumerator representing the device type followed by
-        an integer representing the index of the device.
-        Default: ``None``.
-    copy {bool, None}, optional
-        Boolean indicating whether or not to copy the input.
-
-        * If `copy``is ``True``, the input will always be copied.
-        * If ``False``, a ``BufferError`` will be raised if a copy is deemed
-          necessary.
-        * If ``None``, a copy will be made only if deemed necessary, otherwise,
-          the existing memory buffer will be reused.
-
-        Default: ``None``.
-
-    Returns
-    -------
-    out : dpnp_array
-        Returns a new dpnp array containing the data from another array
-        (obj) with the ``__dlpack__`` method on the same device as object.
-
-    Raises
-    ------
-    TypeError:
-        if `obj` does not implement ``__dlpack__`` method
-    ValueError:
-        if the input array resides on an unsupported device
-
-    """
-
-    usm_res = dpt.from_dlpack(obj, device=device, copy=copy)
-    return dpnp_array._create_from_usm_ndarray(usm_res)
-
-
 def get_dpnp_descriptor(
     ext_obj,
     copy_when_strides=True,

dpnp/dpnp_iface_arraycreation.py

@@ -75,6 +75,7 @@
     "fromfunction",
     "fromiter",
     "fromstring",
+    "from_dlpack",
     "full",
     "full_like",
     "geomspace",
@@ -2047,6 +2048,93 @@ def fromstring(
     )
 
 
+def from_dlpack(x, /, *, device=None, copy=None):
+    """
+    Constructs :class:`dpnp.ndarray` or :class:`numpy.ndarray` instance from
+    a Python object `x` that implements ``__dlpack__`` protocol.
+
+    For full documentation refer to :obj:`numpy.from_dlpack`.
+
+    Parameters
+    ----------
+    x : object
+        A Python object representing an array that implements the ``__dlpack__``
+        and ``__dlpack_device__`` methods.
+    device : {None, string, tuple, device}, optional
+        Device where the output array is to be placed. `device` keyword values
+        can be:
+
+        * ``None`` : The data remains on the same device.
+        * oneAPI filter selector string : SYCL device selected by filter
+          selector string.
+        * :class:`dpctl.SyclDevice` : Explicit SYCL device that must correspond
+          to a non-partitioned SYCL device.
+        * :class:`dpctl.SyclQueue` : Implies SYCL device targeted by the SYCL
+          queue.
+        * :class:`dpctl.tensor.Device` : Implies SYCL device
+          ``device.sycl_queue``. The `device` object is obtained via
+          :attr:`dpctl.tensor.usm_ndarray.device`.
+        * ``(device_type, device_id)`` : 2-tuple matching the format of the
+          output of the ``__dlpack_device__`` method: an integer enumerator
+          representing the device type followed by an integer representing
+          the index of the device. The only supported :class:`dpnp.DLDeviceType`
+          device types are ``"kDLCPU"`` and ``"kDLOneAPI"``.
+
+        Default: ``None``.
+    copy : {bool, None}, optional
+        Boolean indicating whether or not to copy the input.
+
+        * If `copy` is ``True``, the input will always be copied.
+        * If ``False``, a ``BufferError`` will be raised if a copy is deemed
+          necessary.
+        * If ``None``, a copy will be made only if deemed necessary, otherwise,
+          the existing memory buffer will be reused.
+
+        Default: ``None``.
+
+    Returns
+    -------
+    out : {dpnp.ndarray, numpy.ndarray}
+        An array containing the data in `x`. When `copy` is ``None`` or
+        ``False``, this may be a view into the original memory.
+        The type of the returned object depends on where the data backing up
+        input object `x` resides. If it resides in a USM allocation on a SYCL
+        device, the type :class:`dpnp.ndarray` is returned, otherwise if it
+        resides on ``"kDLCPU"`` device the type is :class:`numpy.ndarray`, and
+        otherwise an exception is raised.
+
+    Raises
+    ------
+    TypeError
+        if `obj` does not implement ``__dlpack__`` method
+    ValueError
+        if data of the input object resides on an unsupported device
+
+    Notes
+    -----
+    If the return type is :class:`dpnp.ndarray`, the associated SYCL queue is
+    derived from the `device` keyword. When `device` keyword value has type
+    :class:`dpctl.SyclQueue`, the explicit queue instance is used, when `device`
+    keyword value has type :class:`dpctl.tensor.Device`, the
+    ``device.sycl_queue`` is used. In all other cases, the cached SYCL queue
+    corresponding to the implied SYCL device is used.
+
+    Examples
+    --------
+    >>> import dpnp as np
+    >>> import numpy
+    >>> x = numpy.arange(10)
+    >>> # create a view of the numpy array "x" in dpnp:
+    >>> y = np.from_dlpack(x)
+
+    """
+
+    result = dpt.from_dlpack(x, device=device, copy=copy)
+    if isinstance(result, dpt.usm_ndarray):
+        return dpnp_array._create_from_usm_ndarray(result)
+    return result
+
+
 def full(
     shape,
     fill_value,

dpnp/dpnp_iface_indexing.py

@@ -69,6 +69,7 @@
     "fill_diagonal",
     "flatnonzero",
     "indices",
+    "iterable",
     "ix_",
     "mask_indices",
     "ndindex",
@@ -1033,6 +1034,47 @@ def indices(
     return res
 
 
+def iterable(y):
+    """
+    Check whether or not an object can be iterated over.
+
+    For full documentation refer to :obj:`numpy.iterable`.
+
+    Parameters
+    ----------
+    y : object
+        Input object.
+
+    Returns
+    -------
+    out : bool
+        Return ``True`` if the object has an iterator method or is a sequence
+        and ``False`` otherwise.
+
+    Examples
+    --------
+    >>> import dpnp as np
+    >>> np.iterable([1, 2, 3])
+    True
+    >>> np.iterable(2)
+    False
+
+    In most cases, the results of ``np.iterable(obj)`` are consistent with
+    ``isinstance(obj, collections.abc.Iterable)``. One notable exception is
+    the treatment of 0-dimensional arrays:
+
+    >>> from collections.abc import Iterable
+    >>> a = np.array(1.0)  # 0-dimensional array
+    >>> isinstance(a, Iterable)
+    True
+    >>> np.iterable(a)
+    False
+
+    """
+
+    return numpy.iterable(y)
+
+
 def ix_(*args):
     """Construct an open mesh from multiple sequences.