Merge branch 'master' into impl_vecdot

Author: vtavana

.github/workflows/build-sphinx.yml

@@ -76,11 +76,11 @@ jobs:
 
       - name: Install Intel OneAPI
         run: |
-          sudo apt-get install intel-oneapi-mkl                \
-                               intel-oneapi-mkl-devel          \
-                               intel-oneapi-tbb-devel          \
-                               intel-oneapi-libdpstd-devel     \
-                               intel-oneapi-compiler-dpcpp-cpp
+          sudo apt-get install intel-oneapi-mkl-2024.2*                \
+                               intel-oneapi-mkl-devel-2024.2*          \
+                               intel-oneapi-tbb-devel-2021.13*         \
+                               intel-oneapi-libdpstd-devel-2022.6*     \
+                               intel-oneapi-compiler-dpcpp-cpp-2024.2*
 
       # required by sphinxcontrib-spelling extension
       - name: Install enchant package

.github/workflows/conda-package.yml

@@ -29,6 +29,7 @@ env:
       test_copy.py
       test_counting.py
       test_fft.py
+      test_fill.py
       test_flat.py
       test_histogram.py
       test_indexing.py
@@ -63,6 +64,7 @@ env:
       third_party/cupy/statistics_tests/test_histogram.py
       third_party/cupy/statistics_tests/test_meanvar.py
       third_party/cupy/test_ndim.py
+      third_party/cupy/test_type_routines.py
   VER_JSON_NAME: 'version.json'
   VER_SCRIPT1: "import json; f = open('version.json', 'r'); j = json.load(f); f.close(); "
   VER_SCRIPT2: "d = j['dpnp'][0]; print('='.join((d[s] for s in ('version', 'build'))))"
@@ -142,6 +144,8 @@ jobs:
 
       - name: Build conda package
         run: conda build --no-test --python ${{ matrix.python }} --numpy 2.0 ${{ env.CHANNELS }} conda-recipe
+        env:
+          MAX_BUILD_CMPL_MKL_VERSION: '2024.3a0'
 
       - name: Upload artifact
         uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3

.github/workflows/generate_coverage.yaml

@@ -49,11 +49,11 @@ jobs:
       - name: Install latest Intel OneAPI
         if: env.INSTALL_ONE_API == 'yes'
         run: |
-          sudo apt-get install intel-oneapi-mkl                \
-                               intel-oneapi-mkl-devel          \
-                               intel-oneapi-tbb-devel          \
-                               intel-oneapi-libdpstd-devel     \
-                               intel-oneapi-compiler-dpcpp-cpp
+          sudo apt-get install intel-oneapi-mkl-2024.2*                \
+                               intel-oneapi-mkl-devel-2024.2*          \
+                               intel-oneapi-tbb-devel-2021.13*         \
+                               intel-oneapi-libdpstd-devel-2022.6*     \
+                               intel-oneapi-compiler-dpcpp-cpp-2024.2*
 
       - name: Install Lcov
         run: |

.github/workflows/pre-commit.yml

@@ -29,7 +29,7 @@ jobs:
         uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
 
       - name: Set up python
-        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
+        uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
         with:
           python-version: '3.12'
 

conda-recipe/meta.yaml

@@ -1,5 +1,6 @@
+{% set max_compiler_and_mkl_version = environ.get("MAX_BUILD_CMPL_MKL_VERSION", "2026.0a0") %}
 {% set required_compiler_and_mkl_version = "2024.2" %}
-{% set required_dpctl_version = "0.18.0*" %}
+{% set required_dpctl_version = "0.18.1" %}
 
 package:
     name: dpnp
@@ -17,14 +18,14 @@ requirements:
       - ninja
       - git
       - dpctl >={{ required_dpctl_version }}
-      - mkl-devel-dpcpp >={{ required_compiler_and_mkl_version }}
+      - mkl-devel-dpcpp >={{ required_compiler_and_mkl_version }},<{{ max_compiler_and_mkl_version }}
       - onedpl-devel
       - tbb-devel
       - wheel
       - scikit-build
     build:
       - {{ compiler('cxx') }}
-      - {{ compiler('dpcpp') }} >={{ required_compiler_and_mkl_version }}
+      - {{ compiler('dpcpp') }} >={{ required_compiler_and_mkl_version }},<{{ max_compiler_and_mkl_version }}
       - sysroot_linux-64 >=2.28 # [linux]
     run:
       - python

dpnp/dpnp_algo/dpnp_arraycreation.py

@@ -1,3 +1,29 @@
+# -*- coding: utf-8 -*-
+# *****************************************************************************
+# Copyright (c) 2016-2024, Intel Corporation
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+# - Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# - Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+# THE POSSIBILITY OF SUCH DAMAGE.
+# *****************************************************************************
+
 import math
 import operator
 

dpnp/dpnp_algo/dpnp_fill.py

@@ -0,0 +1,78 @@
+# -*- coding: utf-8 -*-
+# *****************************************************************************
+# Copyright (c) 2016-2024, Intel Corporation
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+# - Redistributions of source code must retain the above copyright notice,
+#   this list of conditions and the following disclaimer.
+# - Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+# THE POSSIBILITY OF SUCH DAMAGE.
+# *****************************************************************************
+
+from numbers import Number
+
+import dpctl.tensor as dpt
+import dpctl.utils as dpu
+from dpctl.tensor._ctors import _cast_fill_val
+from dpctl.tensor._tensor_impl import (
+    _copy_usm_ndarray_into_usm_ndarray,
+    _full_usm_ndarray,
+    _zeros_usm_ndarray,
+)
+
+import dpnp
+
+
+def dpnp_fill(arr, val):
+    arr = dpnp.get_usm_ndarray(arr)
+    exec_q = arr.sycl_queue
+
+    # if val is an array, process it
+    if dpnp.is_supported_array_type(val):
+        val = dpnp.get_usm_ndarray(val)
+        if val.shape != ():
+            raise ValueError("`val` must be a scalar or 0D-array")
+        if dpu.get_execution_queue((exec_q, val.sycl_queue)) is None:
+            raise dpu.ExecutionPlacementError(
+                "Input arrays have incompatible queues."
+            )
+        a_val = dpt.astype(val, arr.dtype)
+        a_val = dpt.broadcast_to(a_val, arr.shape)
+        _manager = dpu.SequentialOrderManager[exec_q]
+        dep_evs = _manager.submitted_events
+        h_ev, c_ev = _copy_usm_ndarray_into_usm_ndarray(
+            src=a_val, dst=arr, sycl_queue=exec_q, depends=dep_evs
+        )
+        _manager.add_event_pair(h_ev, c_ev)
+        return
+    elif not isinstance(val, (Number, dpnp.bool)):
+        raise TypeError(
+            f"array cannot be filled with `val` of type {type(val)}"
+        )
+    val = _cast_fill_val(val, arr.dtype)
+
+    _manager = dpu.SequentialOrderManager[exec_q]
+    dep_evs = _manager.submitted_events
+
+    # can leverage efficient memset when val is 0
+    if arr.flags["FORC"] and val == 0:
+        h_ev, zeros_ev = _zeros_usm_ndarray(arr, exec_q, depends=dep_evs)
+        _manager.add_event_pair(h_ev, zeros_ev)
+    else:
+        h_ev, fill_ev = _full_usm_ndarray(val, arr, exec_q, depends=dep_evs)
+        _manager.add_event_pair(h_ev, fill_ev)

dpnp/dpnp_array.py

@@ -928,13 +928,16 @@ def fill(self, value):
         """
         Fill the array with a scalar value.
 
+        For full documentation refer to :obj:`numpy.ndarray.fill`.
+
         Parameters
         ----------
-        value : scalar
+        value : {dpnp.ndarray, usm_ndarray, scalar}
             All elements of `a` will be assigned this value.
 
         Examples
         --------
+        >>> import dpnp as np
         >>> a = np.array([1, 2])
         >>> a.fill(0)
         >>> a
@@ -946,8 +949,10 @@ def fill(self, value):
 
         """
 
-        for i in range(self.size):
-            self.flat[i] = value
+        # lazy import avoids circular imports
+        from .dpnp_algo.dpnp_fill import dpnp_fill
+
+        dpnp_fill(self, value)
 
     @property
     def flags(self):

dpnp/dpnp_iface_logic.py

@@ -64,6 +64,7 @@
     "iscomplex",
     "iscomplexobj",
     "isfinite",
+    "isfortran",
     "isinf",
     "isnan",
     "isneginf",
@@ -991,6 +992,76 @@ def iscomplexobj(x):
 )
 
 
+def isfortran(a):
+    """
+    Check if the array is Fortran contiguous but *not* C contiguous.
+
+    This function is obsolete. If you only want to check if an array is Fortran
+    contiguous use ``a.flags.f_contiguous`` instead.
+
+    For full documentation refer to :obj:`numpy.isfortran`.
+
+    Parameters
+    ----------
+    a : {dpnp.ndarray, usm_ndarray}
+        Input array.
+
+    Returns
+    -------
+    isfortran : bool
+        Returns ``True`` if the array is Fortran contiguous
+        but *not* C contiguous.
+
+    Examples
+    --------
+    :obj:`dpnp.array` allows to specify whether the array is written in
+    C-contiguous order (last index varies the fastest), or FORTRAN-contiguous
+    order in memory (first index varies the fastest).
+
+    >>> import dpnp as np
+    >>> a = np.array([[1, 2, 3], [4, 5, 6]], order='C')
+    >>> a
+    array([[1, 2, 3],
+           [4, 5, 6]])
+    >>> np.isfortran(a)
+    False
+
+    >>> b = np.array([[1, 2, 3], [4, 5, 6]], order='F')
+    >>> b
+    array([[1, 2, 3],
+           [4, 5, 6]])
+    >>> np.isfortran(b)
+    True
+
+    The transpose of a C-ordered array is a FORTRAN-ordered array.
+
+    >>> a = np.array([[1, 2, 3], [4, 5, 6]], order='C')
+    >>> a
+    array([[1, 2, 3],
+           [4, 5, 6]])
+    >>> np.isfortran(a)
+    False
+    >>> b = a.T
+    >>> b
+    array([[1, 4],
+           [2, 5],
+           [3, 6]])
+    >>> np.isfortran(b)
+    True
+
+    C-ordered arrays evaluate as ``False`` even if they are also
+    FORTRAN-ordered.
+
+    >>> np.isfortran(np.array([1, 2], order='F'))
+    False
+
+    """
+
+    dpnp.check_supported_arrays_type(a)
+
+    return a.flags.fnc
+
+
 _ISINF_DOCSTRING = """
 Test if each element of input array is an infinity.
 

dpnp/dpnp_iface_statistics.py

@@ -370,7 +370,7 @@ def correlate(x1, x2, mode="valid"):
     -----------
     Input arrays are supported as :obj:`dpnp.ndarray`.
     Size and shape of input arrays are supported to be equal.
-    Parameter `mode` is supported only with default value ``"valid``.
+    Parameter `mode` is supported only with default value ``"valid"``.
     Otherwise the function will be executed sequentially on CPU.
     Input array data types are limited by supported DPNP :ref:`Data types`.
 

dpnp/dpnp_utils/dpnp_utils_einsum.py

@@ -33,9 +33,8 @@
 from dpctl.utils import ExecutionPlacementError
 
 import dpnp
-from dpnp.dpnp_utils import get_usm_allocations
-
-from ..dpnp_array import dpnp_array
+from dpnp.dpnp_array import dpnp_array
+from dpnp.dpnp_utils import get_usm_allocations, map_dtype_to_device
 
 _einsum_symbols = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
 
@@ -1027,17 +1026,16 @@ def dpnp_einsum(
                 "Input and output allocation queues are not compatible"
             )
 
-    result_dtype = dpnp.result_type(*arrays) if dtype is None else dtype
     for id, a in enumerate(operands):
         if dpnp.isscalar(a):
+            scalar_dtype = map_dtype_to_device(type(a), exec_q.sycl_device)
             operands[id] = dpnp.array(
-                a, dtype=result_dtype, usm_type=res_usm_type, sycl_queue=exec_q
+                a, dtype=scalar_dtype, usm_type=res_usm_type, sycl_queue=exec_q
             )
+            arrays.append(operands[id])
     result_dtype = dpnp.result_type(*arrays) if dtype is None else dtype
-    if order in ["a", "A"]:
-        order = (
-            "F" if not any(arr.flags.c_contiguous for arr in arrays) else "C"
-        )
+    if order in "aA":
+        order = "F" if all(arr.flags.fnc for arr in arrays) else "C"
 
     input_subscripts = [
         _parse_ellipsis_subscript(sub, idx, ndim=arr.ndim)