Merge 2bea896 into a098910

Author: vtavana

.github/workflows/conda-package.yml

@@ -107,7 +107,7 @@ jobs:
 
     strategy:
       matrix:
-        python: ['3.9', '3.10', '3.11', '3.12']
+        python: ['3.9', '3.10', '3.11']
 
     continue-on-error: true
 
@@ -148,7 +148,7 @@ jobs:
 
       - name: Test conda channel
         run: |
-          mamba search ${{ env.PACKAGE_NAME }} -c ${{ env.channel-path }} --override-channels --info --json > ${{ env.ver-json-path }}
+          conda search ${{ env.PACKAGE_NAME }} -c ${{ env.channel-path }} --override-channels --info --json > ${{ env.ver-json-path }}
           cat ${{ env.ver-json-path }}
 
       - name: Get package version
@@ -182,7 +182,7 @@ jobs:
         id: run_tests_linux
         uses: nick-fields/retry@7152eba30c6575329ac0576536151aca5a72780e # v3.0.0
         with:
-          timeout_minutes: 10
+          timeout_minutes: 12
           max_attempts: ${{ env.RUN_TESTS_MAX_ATTEMPTS }}
           retry_on: any
           command: |
@@ -193,7 +193,7 @@ jobs:
             python -m pytest -n auto -ra --pyargs ${{ env.PACKAGE_NAME }}.tests
 
   test_linux_all_dtypes:
-    name: Test ['ubuntu-latest', python='${{ matrix.python }}']
+    name: Test ['ubuntu-latest-all-dtypes', python='${{ matrix.python }}']
 
     needs: build
 
@@ -274,7 +274,7 @@ jobs:
         env:
             DPNP_TEST_ALL_INT_TYPES: 1
         run: |
-            pytest -n auto -ra --pyargs ${{ env.PACKAGE_NAME }}.tests
+            pytest -ra --pyargs ${{ env.PACKAGE_NAME }}.tests
 
   test_windows:
     name: Test ['windows-2019', python='${{ matrix.python }}']
@@ -289,7 +289,7 @@ jobs:
 
     strategy:
       matrix:
-        python: ['3.9', '3.10', '3.11', '3.12']
+        python: ['3.9', '3.10', '3.11']
 
     continue-on-error: true
 
@@ -348,7 +348,7 @@ jobs:
       - name: Test conda channel
         run: |
           @echo on
-          mamba search ${{ env.PACKAGE_NAME }} -c ${{ env.channel-path }} --override-channels --info --json > ${{ env.ver-json-path }}
+          conda search ${{ env.PACKAGE_NAME }} -c ${{ env.channel-path }} --override-channels --info --json > ${{ env.ver-json-path }}
 
       - name: Dump version.json
         run: more ${{ env.ver-json-path }}
@@ -409,7 +409,7 @@ jobs:
             python -m pytest -n auto -ra --pyargs ${{ env.PACKAGE_NAME }}.tests
 
   test_windows_all_dtypes:
-    name: Test ['windows-2019', python='${{ matrix.python }}']
+    name: Test ['windows-2019-all-dtypes', python='${{ matrix.python }}']
 
     needs: build
 

dpnp/backend/kernels/dpnp_krnl_common.cpp

@@ -40,7 +40,7 @@
  * sycl::ext::oneapi::experimental::properties was added.
  */
 #ifndef __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT
-#define __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT 20241129
+#define __SYCL_COMPILER_REDUCTION_PROPERTIES_SUPPORT 20241208L
 #endif
 
 namespace mkl_blas = oneapi::mkl::blas;

dpnp/backend/kernels/elementwise_functions/i0.hpp

@@ -32,7 +32,7 @@
  * sycl::ext::intel::math::cyl_bessel_i0(x) is fully resolved.
  */
 #ifndef __SYCL_COMPILER_BESSEL_I0_SUPPORT
-#define __SYCL_COMPILER_BESSEL_I0_SUPPORT 20241114L
+#define __SYCL_COMPILER_BESSEL_I0_SUPPORT 20241208L
 #endif
 
 #if __SYCL_COMPILER_VERSION >= __SYCL_COMPILER_BESSEL_I0_SUPPORT

dpnp/dpnp_iface_linearalgebra.py

@@ -37,10 +37,12 @@
 
 """
 
+# pylint: disable=no-name-in-module
 import numpy
 
 import dpnp
 
+from .dpnp_utils import map_dtype_to_device
 from .dpnp_utils.dpnp_utils_einsum import dpnp_einsum
 from .dpnp_utils.dpnp_utils_linearalgebra import (
     dpnp_dot,
@@ -64,6 +66,20 @@
 ]
 
 
+# TODO: implement a specific scalar-array kernel
+def _call_multiply(a, b, out=None):
+    """Call multiply function for special cases of scalar-array dots."""
+
+    sc, arr = (a, b) if dpnp.isscalar(a) else (b, a)
+    sc_dtype = map_dtype_to_device(type(sc), arr.sycl_device)
+    res_dtype = dpnp.result_type(sc_dtype, arr)
+    if out is not None and out.dtype == arr.dtype:
+        res = dpnp.multiply(a, b, out=out)
+    else:
+        res = dpnp.multiply(a, b, dtype=res_dtype)
+    return dpnp.get_result_array(res, out, casting="no")
+
+
 def dot(a, b, out=None):
     """
     Dot product of `a` and `b`.
@@ -137,8 +153,7 @@ def dot(a, b, out=None):
             raise ValueError("Only C-contiguous array is acceptable.")
 
     if dpnp.isscalar(a) or dpnp.isscalar(b):
-        # TODO: use specific scalar-vector kernel
-        return dpnp.multiply(a, b, out=out)
+        return _call_multiply(a, b, out=out)
 
     a_ndim = a.ndim
     b_ndim = b.ndim
@@ -627,8 +642,7 @@ def inner(a, b):
     dpnp.check_supported_arrays_type(a, b, scalar_type=True)
 
     if dpnp.isscalar(a) or dpnp.isscalar(b):
-        # TODO: use specific scalar-vector kernel
-        return dpnp.multiply(a, b)
+        return _call_multiply(a, b)
 
     if a.ndim == 0 or b.ndim == 0:
         # TODO: use specific scalar-vector kernel
@@ -706,8 +720,7 @@ def kron(a, b):
     dpnp.check_supported_arrays_type(a, b, scalar_type=True)
 
     if dpnp.isscalar(a) or dpnp.isscalar(b):
-        # TODO: use specific scalar-vector kernel
-        return dpnp.multiply(a, b)
+        return _call_multiply(a, b)
 
     a_ndim = a.ndim
     b_ndim = b.ndim
@@ -1043,8 +1056,7 @@ def tensordot(a, b, axes=2):
             raise ValueError(
                 "One of the inputs is scalar, axes should be zero."
             )
-        # TODO: use specific scalar-vector kernel
-        return dpnp.multiply(a, b)
+        return _call_multiply(a, b)
 
     return dpnp_tensordot(a, b, axes=axes)
 
@@ -1107,13 +1119,13 @@ def vdot(a, b):
         if b.size != 1:
             raise ValueError("The second array should be of size one.")
         a_conj = numpy.conj(a)
-        return dpnp.multiply(a_conj, b)
+        return _call_multiply(a_conj, b)
 
     if dpnp.isscalar(b):
         if a.size != 1:
             raise ValueError("The first array should be of size one.")
         a_conj = dpnp.conj(a)
-        return dpnp.multiply(a_conj, b)
+        return _call_multiply(a_conj, b)
 
     if a.ndim == 1 and b.ndim == 1:
         return dpnp_dot(a, b, out=None, conjugate=True)

dpnp/dpnp_iface_nanfunctions.py

@@ -987,7 +987,7 @@ def nanstd(
     ddof : {int, float}, optional
         Means Delta Degrees of Freedom. The divisor used in calculations
         is ``N - ddof``, where ``N`` the number of non-NaN elements.
-        Default: `0.0`.
+        Default: ``0.0``.
     keepdims : {None, bool}, optional
         If ``True``, the reduced axes (dimensions) are included in the result
         as singleton dimensions, so that the returned array remains
@@ -1087,7 +1087,7 @@ def nanvar(
     ddof : {int, float}, optional
         Means Delta Degrees of Freedom.  The divisor used in calculations
         is ``N - ddof``, where ``N`` represents the number of non-NaN elements.
-        Default: `0.0`.
+        Default: ``0.0``.
     keepdims : {None, bool}, optional
         If ``True``, the reduced axes (dimensions) are included in the result
         as singleton dimensions, so that the returned array remains

dpnp/fft/dpnp_utils_fft.py

@@ -282,7 +282,10 @@ def _copy_array(x, complex_input):
         # r2c FFT, if input is integer or float16 dtype, convert to
         # float32 or float64 depending on device capabilities
         copy_flag = True
-        dtype = map_dtype_to_device(dpnp.float64, x.sycl_device)
+        if dtype == dpnp.float16:
+            dtype = dpnp.float32
+        else:
+            dtype = map_dtype_to_device(dpnp.float64, x.sycl_device)
 
     if copy_flag:
         x_copy = dpnp.empty_like(x, dtype=dtype, order="C")

dpnp/tests/helper.py

@@ -85,24 +85,19 @@ def assert_dtype_allclose(
                 assert dpnp_arr.dtype == numpy_arr.dtype
 
 
-def get_integer_dtypes():
+def get_integer_dtypes(no_unsigned=False):
     """
     Build a list of integer types supported by DPNP.
     """
 
+    dtypes = [dpnp.int32, dpnp.int64]
+
     if config.all_int_types:
-        return [
-            dpnp.int8,
-            dpnp.int16,
-            dpnp.int32,
-            dpnp.int64,
-            dpnp.uint8,
-            dpnp.uint16,
-            dpnp.uint32,
-            dpnp.uint64,
-        ]
+        dtypes += [dpnp.int8, dpnp.int16]
+        if not no_unsigned:
+            dtypes += [dpnp.uint8, dpnp.uint16, dpnp.uint32, dpnp.uint64]
 
-    return [dpnp.int32, dpnp.int64]
+    return dtypes
 
 
 def get_complex_dtypes(device=None):
@@ -147,17 +142,25 @@ def get_float_complex_dtypes(no_float16=True, device=None):
     return dtypes
 
 
+def get_abs_array(data, dtype=None):
+    if numpy.issubdtype(dtype, numpy.unsignedinteger):
+        data = numpy.abs(data)
+    return numpy.array(data, dtype=dtype)
+
+
 def get_all_dtypes(
     no_bool=False,
     no_float16=True,
     no_complex=False,
     no_none=False,
-    device=None,
     xfail_dtypes=None,
     exclude=None,
+    no_unsigned=False,
+    device=None,
 ):
     """
-    Build a list of types supported by DPNP based on input flags and device capabilities.
+    Build a list of types supported by DPNP based on
+    input flags and device capabilities.
     """
 
     dev = dpctl.select_default_device() if device is None else device
@@ -166,7 +169,7 @@ def get_all_dtypes(
     dtypes = [dpnp.bool] if not no_bool else []
 
     # add integer types
-    dtypes.extend(get_integer_dtypes())
+    dtypes.extend(get_integer_dtypes(no_unsigned=no_unsigned))
 
     # add floating types
     dtypes.extend(get_float_dtypes(no_float16=no_float16, device=dev))
@@ -194,7 +197,13 @@ def not_excluded(dtype):
 
 
 def generate_random_numpy_array(
-    shape, dtype=None, hermitian=False, seed_value=None, low=-10, high=10
+    shape,
+    dtype=None,
+    order="C",
+    hermitian=False,
+    seed_value=None,
+    low=-10,
+    high=10,
 ):
     """
     Generate a random numpy array with the specified shape and dtype.
@@ -210,6 +219,9 @@ def generate_random_numpy_array(
         Desired data-type for the output array.
         If not specified, data type will be determined by numpy.
         Default : ``None``
+    order : {"C", "F"}, optional
+        Specify the memory layout of the output array.
+        Default: ``"C"``.
     hermitian : bool, optional
         If True, generates a Hermitian (symmetric if `dtype` is real) matrix.
         Default : ``False``
@@ -226,7 +238,7 @@ def generate_random_numpy_array(
     Returns
     -------
     out : numpy.ndarray
-        A random numpy array of the specified shape and dtype.
+        A random numpy array of the specified shape, dtype and memory layout.
         The array is Hermitian or symmetric if `hermitian` is True.
 
     Note:
@@ -239,10 +251,13 @@ def generate_random_numpy_array(
         seed_value = 42
     numpy.random.seed(seed_value)
 
+    if numpy.issubdtype(dtype, numpy.unsignedinteger):
+        low = 0
+
     # dtype=int is needed for 0d arrays
     size = numpy.prod(shape, dtype=int)
     a = numpy.random.uniform(low, high, size).astype(dtype)
-    if numpy.issubdtype(a.dtype, numpy.complexfloating):
+    if numpy.issubdtype(dtype, numpy.complexfloating):
         a += 1j * numpy.random.uniform(low, high, size)
 
     a = a.reshape(shape)
@@ -256,6 +271,10 @@ def generate_random_numpy_array(
             a = a.reshape(orig_shape)
         else:
             a = numpy.conj(a.T) @ a
+
+    # a.reshape(shape) returns an array in C order by default
+    if order != "C" and a.ndim > 1:
+        a = numpy.array(a, order=order)
     return a