Merge branch 'master' into convolve

Author: AlexanderKalistratov

.github/workflows/array-api-skips.txt

@@ -6,3 +6,9 @@ array_api_tests/test_operators_and_elementwise_functions.py::test_clip
 # unexpected result is returned - unmute when dpctl-1986 is resolved
 array_api_tests/test_operators_and_elementwise_functions.py::test_asin
 array_api_tests/test_operators_and_elementwise_functions.py::test_asinh
+
+# advanced indexing relating issues (waiting a fix from dpctl)
+array_api_tests/test_array_object.py::test_getitem_arrays_and_ints_1[1]
+array_api_tests/test_array_object.py::test_getitem_arrays_and_ints_1[None]
+array_api_tests/test_array_object.py::test_getitem_arrays_and_ints_2[1]
+array_api_tests/test_array_object.py::test_getitem_arrays_and_ints_2[None]

.github/workflows/check-mkl-interfaces.yaml

@@ -48,7 +48,7 @@ jobs:
 
       - name: Merge conda env files
         run: |
-          conda-merge ${{ env.build-with-oneapi-env }} ${{ env.dpctl-pkg-env }} ${{ env.oneapi-pkgs-env }} > ${{ env.environment-file }}
+          conda-merge ${{ env.dpctl-pkg-env }} ${{ env.oneapi-pkgs-env }} ${{ env.build-with-oneapi-env }} > ${{ env.environment-file }}
           cat ${{ env.environment-file }}
 
       - name: Upload artifact

.github/workflows/conda-package.yml

@@ -93,13 +93,13 @@ jobs:
         continue-on-error: true
         run: conda build --no-test --python ${{ matrix.python }} --numpy 2.0 ${{ env.channels-list }} conda-recipe
         env:
-          MAX_BUILD_CMPL_MKL_VERSION: '2025.1a0'
+          MAX_BUILD_CMPL_MKL_VERSION: '2025.2a0'
 
       - name: ReBuild conda package
         if: steps.build_conda_pkg.outcome == 'failure'
         run: conda build --no-test --python ${{ matrix.python }} --numpy 2.0 ${{ env.channels-list }} conda-recipe
         env:
-          MAX_BUILD_CMPL_MKL_VERSION: '2025.1a0'
+          MAX_BUILD_CMPL_MKL_VERSION: '2025.2a0'
 
       - name: Upload artifact
         uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
@@ -625,6 +625,7 @@ jobs:
           python -m pytest --json-report --json-report-file=${{ env.json-report-file }} --disable-deadline --skips-file ${{ env.array-api-skips-file }} array_api_tests || true
         env:
           ARRAY_API_TESTS_MODULE: 'dpnp'
+          ARRAY_API_TESTS_VERSION: '2024.12'
           SYCL_CACHE_PERSISTENT: 1
         working-directory: ${{ env.array-api-tests-path }}
 

.github/workflows/openssf-scorecard.yml

@@ -68,6 +68,6 @@ jobs:
 
       # Upload the results to GitHub's code scanning dashboard.
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@5f8171a638ada777af81d42b55959a643bb29017 # v3.28.12
+        uses: github/codeql-action/upload-sarif@1b549b9259bda1cb5ddde3b41741a82a2d15a841 # v3.28.13
         with:
           sarif_file: results.sarif

.github/workflows/pre-commit.yml

@@ -29,7 +29,7 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
 
       - name: Set up python
-        uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
+        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
         with:
           python-version: '3.13'
 

.pre-commit-config.yaml

@@ -2,13 +2,13 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
 -   repo: https://github.com/PyCQA/bandit
-    rev: '1.7.9'
+    rev: '1.8.3'
     hooks:
     -   id: bandit
         pass_filenames: false
         args: ["-r", "dpnp", "-lll"]
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
     -   id: check-ast
     -   id: check-builtin-literals
@@ -44,17 +44,18 @@ repos:
     -   id: rst-inline-touching-normal
     -   id: text-unicode-replacement-char
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
     -   id: codespell
+        args: ["-L", "abd"]  # ignore "abd" used in einsum tests
         additional_dependencies:
             - tomli
 -   repo: https://github.com/psf/black
-    rev: 24.4.2
+    rev: 25.1.0
     hooks:
     -   id: black
 -   repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+    rev: 6.0.1
     hooks:
     -   id: isort
         name: isort (python)
@@ -65,20 +66,20 @@ repos:
         name: isort (pyi)
         types: [pyi]
 -   repo: https://github.com/pycqa/flake8
-    rev: 7.1.0
+    rev: 7.1.2
     hooks:
     -   id: flake8
         args: ["--config=.flake8"]
         additional_dependencies:
             - flake8-docstrings==1.7.0
-            - flake8-bugbear==24.4.26
+            - flake8-bugbear==24.12.12
 -   repo: https://github.com/pocc/pre-commit-hooks
     rev: v1.3.5
     hooks:
     -   id: clang-format
         args: ["-i"]
 -   repo: https://github.com/gitleaks/gitleaks
-    rev: v8.18.4
+    rev: v8.24.0
     hooks:
     -   id: gitleaks
 -   repo: https://github.com/jumanjihouse/pre-commit-hooks
@@ -102,3 +103,8 @@ repos:
             "--disable=unused-wildcard-import"
             ]
         files: '^dpnp/(dpnp_iface.*|fft|linalg)'
+-   repo: https://github.com/macisamuele/language-formatters-pre-commit-hooks
+    rev: v2.14.0
+    hooks:
+    -   id: pretty-format-toml
+        args: [--autofix]

CHANGELOG.md

@@ -13,16 +13,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 * Added implementation of `dpnp.blackman` [#2363](https://github.com/IntelPython/dpnp/pull/2363)
 * Added implementation of `dpnp.bartlett` [#2366](https://github.com/IntelPython/dpnp/pull/2366)
 * Added implementation of `dpnp.convolve` [#2205](https://github.com/IntelPython/dpnp/pull/2205)
+* Added implementation of `dpnp.kaiser` [#2387](https://github.com/IntelPython/dpnp/pull/2387)
 
 ### Changed
 
-* Extended `dpnp.fft.fftfreq` and `dpnp.fft.rfftfreq` functions to support `dtype` keyword per Python Array API spec 2024.12 [#2384](https://github.com/IntelPython/dpnp/pull/2384)
+* Improved performance of `dpnp.nansum`, `dpnp.nanprod`, `dpnp.nancumsum`, and `dpnp.nancumprod` by reusing `dpnp.nan_to_num` function in implementation of the functions [#2339](https://github.com/IntelPython/dpnp/pull/2339)
 * Allowed input array of `uint64` dtype in `dpnp.bincount` [#2361](https://github.com/IntelPython/dpnp/pull/2361)
 * The vector norms `ord={None, 1, 2, inf}` and the matrix norms `ord={None, 1, 2, inf, "fro", "nuc"}` now consistently return zero for empty arrays, which are arrays with at least one axis of size zero. This change affects `dpnp.linalg.norm`, `dpnp.linalg.vector_norm`, and `dpnp.linalg.matrix_norm`. Previously, dpnp would either raise errors or return zero depending on the parameters provided [#2371](https://github.com/IntelPython/dpnp/pull/2371)
+* Extended `dpnp.fft.fftfreq` and `dpnp.fft.rfftfreq` functions to support `dtype` keyword per Python Array API spec 2024.12 [#2384](https://github.com/IntelPython/dpnp/pull/2384)
+* Updated `dpnp.fix` to return output with the same data-type of input [#2392](https://github.com/IntelPython/dpnp/pull/2392)
 
 ### Fixed
 
 * Resolved an issue with an incorrect result returned due to missing dependency from the strided kernel on a copy event in `dpnp.erf` [#2378](https://github.com/IntelPython/dpnp/pull/2378)
+* Updated `conda create` commands build and install instructions of `Quick start guide` to avoid a compilation error [#2395](https://github.com/IntelPython/dpnp/pull/2395)
 
 
 ## [0.17.0] - 02/26/2025

doc/quick_start_guide.rst

@@ -88,14 +88,18 @@ On Linux:
 
 .. code-block:: bash
 
-    conda create -n build-env dpctl cython dpcpp_linux-64 mkl-devel-dpcpp tbb-devel onedpl-devel cmake scikit-build ninja pytest -c https://software.repos.intel.com/python/conda/ -c conda-forge
+    conda create -n build-env dpctl cython dpcpp_linux-64 mkl-devel-dpcpp tbb-devel \
+          onedpl-devel cmake scikit-build ninja pytest intel-gpu-ocl-icd-system     \
+          -c dppy/label/dev -c https://software.repos.intel.com/python/conda/ -c conda-forge
     conda activate build-env
 
 On Windows:
 
 .. code-block:: bash
 
-    conda create -n build-env dpctl cython dpcpp_win-64 mkl-devel-dpcpp tbb-devel onedpl-devel cmake scikit-build ninja pytest -c https://software.repos.intel.com/python/conda/ -c conda-forge
+    conda create -n build-env dpctl cython dpcpp_win-64 mkl-devel-dpcpp tbb-devel \
+          onedpl-devel cmake scikit-build ninja pytest intel-gpu-ocl-icd-system   \
+          -c dppy/label/dev -c https://software.repos.intel.com/python/conda/ -c conda-forge
     conda activate build-env
 
 To build and install the package on Linux OS, run:

dpnp/backend/extensions/blas/blas_py.cpp

@@ -62,8 +62,7 @@ PYBIND11_MODULE(_blas_impl, m)
     using event_vecT = std::vector<sycl::event>;
 
     {
-        dot_ns::init_dot_dispatch_vector<dot_impl_fn_ptr_t,
-                                         blas_ns::DotContigFactory>(
+        dot_ns::init_dot_dispatch_vector<blas_ns::DotContigFactory>(
             dot_dispatch_vector);
 
         auto dot_pyapi = [&](sycl::queue &exec_q, const arrayT &src1,
@@ -81,8 +80,7 @@ PYBIND11_MODULE(_blas_impl, m)
     }
 
     {
-        dot_ns::init_dot_dispatch_vector<dot_impl_fn_ptr_t,
-                                         blas_ns::DotcContigFactory>(
+        dot_ns::init_dot_dispatch_vector<blas_ns::DotcContigFactory>(
             dotc_dispatch_vector);
 
         auto dotc_pyapi = [&](sycl::queue &exec_q, const arrayT &src1,
@@ -101,8 +99,7 @@ PYBIND11_MODULE(_blas_impl, m)
     }
 
     {
-        dot_ns::init_dot_dispatch_vector<dot_impl_fn_ptr_t,
-                                         blas_ns::DotuContigFactory>(
+        dot_ns::init_dot_dispatch_vector<blas_ns::DotuContigFactory>(
             dotu_dispatch_vector);
 
         auto dotu_pyapi = [&](sycl::queue &exec_q, const arrayT &src1,

dpnp/backend/extensions/blas/dot_common.hpp

@@ -50,14 +50,13 @@ typedef sycl::event (*dot_impl_fn_ptr_t)(sycl::queue &,
 namespace dpctl_td_ns = dpctl::tensor::type_dispatch;
 namespace py = pybind11;
 
-template <typename dispatchT>
 std::pair<sycl::event, sycl::event>
     dot_func(sycl::queue &exec_q,
              const dpctl::tensor::usm_ndarray &vectorX,
              const dpctl::tensor::usm_ndarray &vectorY,
              const dpctl::tensor::usm_ndarray &result,
              const std::vector<sycl::event> &depends,
-             const dispatchT &dot_dispatch_vector)
+             const dot_impl_fn_ptr_t *dot_dispatch_vector)
 {
     const int vectorX_nd = vectorX.get_ndim();
     const int vectorY_nd = vectorY.get_ndim();
@@ -166,12 +165,10 @@ std::pair<sycl::event, sycl::event>
     return std::make_pair(args_ev, dot_ev);
 }
 
-template <typename dispatchT,
-          template <typename fnT, typename T>
-          typename factoryT>
-void init_dot_dispatch_vector(dispatchT dot_dispatch_vector[])
+template <template <typename fnT, typename T> typename factoryT>
+void init_dot_dispatch_vector(dot_impl_fn_ptr_t dot_dispatch_vector[])
 {
-    dpctl_td_ns::DispatchVectorBuilder<dispatchT, factoryT,
+    dpctl_td_ns::DispatchVectorBuilder<dot_impl_fn_ptr_t, factoryT,
                                        dpctl_td_ns::num_types>
         contig;
     contig.populate_dispatch_vector(dot_dispatch_vector);

dpnp/backend/extensions/window/CMakeLists.txt

@@ -26,6 +26,7 @@
 
 set(python_module_name _window_impl)
 set(_module_src
+    ${CMAKE_CURRENT_SOURCE_DIR}/kaiser.cpp
     ${CMAKE_CURRENT_SOURCE_DIR}/window_py.cpp
 )
 

dpnp/backend/extensions/window/common.hpp

@@ -67,12 +67,11 @@ sycl::event window_impl(sycl::queue &q,
     return window_ev;
 }
 
-template <typename dispatchT>
-std::pair<sycl::event, sycl::event>
-    py_window(sycl::queue &exec_q,
+template <typename funcPtrT>
+std::tuple<size_t, char *, funcPtrT>
+    window_fn(sycl::queue &exec_q,
               const dpctl::tensor::usm_ndarray &result,
-              const std::vector<sycl::event> &depends,
-              const dispatchT &window_dispatch_vector)
+              const funcPtrT *window_dispatch_vector)
 {
     dpctl::tensor::validation::CheckWritable::throw_if_not_writable(result);
 
@@ -93,30 +92,48 @@ std::pair<sycl::event, sycl::event>
 
     size_t nelems = result.get_size();
     if (nelems == 0) {
-        return std::make_pair(sycl::event{}, sycl::event{});
+        return std::make_tuple(nelems, nullptr, nullptr);
     }
 
     int result_typenum = result.get_typenum();
     auto array_types = dpctl_td_ns::usm_ndarray_types();
     int result_type_id = array_types.typenum_to_lookup_id(result_typenum);
-    auto fn = window_dispatch_vector[result_type_id];
+    funcPtrT fn = window_dispatch_vector[result_type_id];
 
     if (fn == nullptr) {
         throw std::runtime_error("Type of given array is not supported");
     }
 
     char *result_typeless_ptr = result.get_data();
+    return std::make_tuple(nelems, result_typeless_ptr, fn);
+}
+
+inline std::pair<sycl::event, sycl::event>
+    py_window(sycl::queue &exec_q,
+              const dpctl::tensor::usm_ndarray &result,
+              const std::vector<sycl::event> &depends,
+              const window_fn_ptr_t *window_dispatch_vector)
+{
+    auto [nelems, result_typeless_ptr, fn] =
+        window_fn<window_fn_ptr_t>(exec_q, result, window_dispatch_vector);
+
+    if (nelems == 0) {
+        return std::make_pair(sycl::event{}, sycl::event{});
+    }
+
     sycl::event window_ev = fn(exec_q, result_typeless_ptr, nelems, depends);
     sycl::event args_ev =
         dpctl::utils::keep_args_alive(exec_q, {result}, {window_ev});
 
     return std::make_pair(args_ev, window_ev);
 }
 
-template <template <typename fnT, typename T> typename factoryT>
-void init_window_dispatch_vectors(window_fn_ptr_t window_dispatch_vector[])
+template <typename funcPtrT,
+          template <typename fnT, typename T>
+          typename factoryT>
+void init_window_dispatch_vectors(funcPtrT window_dispatch_vector[])
 {
-    dpctl_td_ns::DispatchVectorBuilder<window_fn_ptr_t, factoryT,
+    dpctl_td_ns::DispatchVectorBuilder<funcPtrT, factoryT,
                                        dpctl_td_ns::num_types>
         contig;
     contig.populate_dispatch_vector(window_dispatch_vector);