Backport gh-2166, gh-2057, gh-2211

.github/workflows/build-sphinx.yml

@@ -104,7 +104,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge

.github/workflows/conda-package.yml

@@ -103,7 +103,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge
@@ -197,7 +196,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge
@@ -327,7 +325,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge
@@ -469,7 +466,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge
@@ -505,7 +501,6 @@ jobs:
     steps:
       - uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge

.github/workflows/generate_coverage.yaml

@@ -62,7 +62,6 @@ jobs:
       - name: Setup miniconda
         uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3.0.4
         with:
-          miniforge-variant: Mambaforge
           miniforge-version: latest
           use-mamba: true
           channels: conda-forge

CHANGELOG.md

@@ -1,9 +1,23 @@
 # Changelog
 All notable changes to this project will be documented in this file.
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.16.1] - 12/XX/2024
+
+This is a bug-fix release.
+
+### Changed
+
+* Changed to use `Miniforge` installer in GutHub 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)
+
+### Fixed
+
+* 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.

README.md

@@ -6,117 +6,76 @@
 [![Build Sphinx](https://github.com/IntelPython/dpnp/workflows/Build%20Sphinx/badge.svg)](https://intelpython.github.io/dpnp)
 [![OpenSSF Scorecard](https://api.securityscorecards.dev/projects/github.com/IntelPython/dpnp/badge)](https://securityscorecards.dev/viewer/?uri=github.com/IntelPython/dpnp)
 
+<img align="left" src="https://spec.oneapi.io/oneapi-logo-white-scaled.jpg" alt="oneAPI logo" width="75"/>
+
 # DPNP - Data Parallel Extension for NumPy*
+
+Data Parallel Extension for NumPy* or `dpnp` is a Python library that
+implements a subset of NumPy* that can be executed on any data parallel device.
+The subset is a drop-in replacement of core NumPy* functions and numerical data types.
+
 [API coverage summary](https://intelpython.github.io/dpnp/reference/comparison.html#summary)
 
 [Full documentation](https://intelpython.github.io/dpnp/)
 
-[DPNP C++ backend documentation](https://intelpython.github.io/dpnp/backend_doc/)
+`Dpnp` is the core part of a larger family of [data-parallel Python libraries and tools](https://www.intel.com/content/www/us/en/developer/tools/oneapi/distribution-for-python.html)
+to program on XPUs.
 
-## Build from source:
-Ensure you have the following prerequisite packages installed:
 
-- `cython`
-- `cmake >=3.21`
-- `dpcpp_linux-64` or `dpcpp_win-64` (depending on your OS)
-- `dpctl`
-- `mkl-devel-dpcpp`
-- `onedpl-devel`
-- `ninja`
-- `numpy >=1.19,<1.25a0`
-- `python`
-- `scikit-build`
-- `setuptools`
-- `sysroot_linux-64 >=2.28` (only on Linux OS)
-- `tbb-devel`
+# Installing
 
-After these steps, `dpnp` can be built in debug mode as follows:
+You can install the library using `conda`, `mamba` or [pip](https://pypi.org/project/dpnp/)
+package managers. It is also available as part of the [Intel(R) Distribution for Python](https://www.intel.com/content/www/us/en/developer/tools/oneapi/distribution-for-python.html)
+(IDP).
 
-```bash
-git clone https://github.com/IntelPython/dpnp
-cd dpnp
-python scripts/build_locally.py
-```
+## Intel(R) Distribution for Python
 
-## Install Wheel Package via pip
-Install DPNP
-```cmd
-python -m pip install --index-url https://software.repos.intel.com/python/pypi dpnp
-```
+You can find the most recent release of `dpnp` every quarter as part of the IDP
+releases.
 
-Set path to Performance Libraries in case of using venv or system Python:
-```cmd
-export LD_LIBRARY_PATH=<path_to_your_env>/lib
-```
+To get the library from the latest release, follow the instructions from
+[Get Started With Intel® Distribution for Python](https://www.intel.com/content/www/us/en/developer/articles/technical/get-started-with-intel-distribution-for-python.html).
 
-It is also required to set following environment variables:
-```cmd
-export OCL_ICD_FILENAMES_RESET=1
-export OCL_ICD_FILENAMES=libintelocl.so
-```
+## Conda
 
-## Run test
-```bash
-pytest
-# or
-pytest tests/test_matmul.py -s -v
-# or
-python -m unittest tests/test_mixins.py
-```
+To install `dpnp` from the Intel(R) conda channel, use the following command:
 
-## Run numpy external test
 ```bash
-. ./0.env.sh
-python -m tests.third_party.numpy_ext
-# or
-python -m tests.third_party.numpy_ext core/tests/test_umath.py
-# or
-python -m tests.third_party.numpy_ext core/tests/test_umath.py::TestHypot::test_simple
+conda install dpnp -c https://software.repos.intel.com/python/conda/ -c conda-forge
 ```
 
-### Building documentation:
+## Pip
+
+The `dpnp` can be installed using `pip` obtaining wheel packages either from
+PyPi or from Intel(R) channel. To install `dpnp` wheel package from Intel(R)
+channel, run the following command:
+
 ```bash
-Prerequisites:
-$ conda install sphinx sphinx_rtd_theme
-Building:
-1. Install dpnp into your python environment
-2. $ cd doc && make html
-3. The documentation will be in doc/_build/html
+python -m pip install --index-url https://software.repos.intel.com/python/pypi dpnp
 ```
 
-## Packaging:
+## Installing the bleeding edge
+
+To try out the latest features, install `dpnp` using our development channel on
+Anaconda cloud:
+
 ```bash
-. ./0.env.sh
-conda-build conda-recipe/
+conda install dpnp -c dppy/label/dev -c https://software.repos.intel.com/python/conda/ -c conda-forge
 ```
 
-## Run benchmark:
-```bash
-cd benchmarks/
 
-asv run --python=python --bench <filename without .py>
-# example:
-asv run --python=python --bench bench_elementwise
+# Building
 
-# or
+Refer to our [Documentation](https://intelpython.github.io/dpnp/quick_start_guide.html)
+for more information on setting up a development environment and building `dpnp`
+from the source.
 
-asv run --python=python --bench <class>.<bench>
-# example:
-asv run --python=python --bench Elementwise.time_square
 
-# add --quick option to run every case once but looks like first execution has additional overheads and takes a lot of time (need to be investigated)
-```
+# Running Tests
 
+Tests are located in folder [dpnp/tests](dpnp/tests).
 
-## Tests matrix:
-| # |Name                                |OS   |distributive|interpreter|python used from|SYCL queue manager|build commands set                                                                                                                              |forced environment                                                                                                       |
-|---|------------------------------------|-----|------------|-----------|:--------------:|:----------------:|------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------|
-|1  |Ubuntu 20.04 Python37               |Linux|Ubuntu 20.04|Python 3.7 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace pytest                                 |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|2  |Ubuntu 20.04 Python38               |Linux|Ubuntu 20.04|Python 3.8 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace pytest                                 |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|3  |Ubuntu 20.04 Python39               |Linux|Ubuntu 20.04|Python 3.9 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace pytest                                 |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|4  |Ubuntu 20.04 External Tests Python37|Linux|Ubuntu 20.04|Python 3.7 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace python -m tests_external.numpy.runtests|cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|5  |Ubuntu 20.04 External Tests Python38|Linux|Ubuntu 20.04|Python 3.8 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace python -m tests_external.numpy.runtests|cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|6  |Ubuntu 20.04 External Tests Python39|Linux|Ubuntu 20.04|Python 3.9 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace python -m tests_external.numpy.runtests|cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|7  |Code style                          |Linux|Ubuntu 20.04|Python 3.8 |  IntelOneAPI   |      local       |python ./setup.py style                                                                                                                         |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis, conda-verify, pycodestyle, autopep8, black     |
-|8  |Valgrind                            |Linux|Ubuntu 20.04|           |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace                                        |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis                                                 |
-|9  |Code coverage                       |Linux|Ubuntu 20.04|Python 3.8 |  IntelOneAPI   |      local       |export DPNP_DEBUG=1 python setup.py clean python setup.py build_clib python setup.py build_ext --inplace                                        |cmake-3.19.2, valgrind, pytest-valgrind, conda-build, pytest, hypothesis, conda-verify, pycodestyle, autopep8, pytest-cov|
+To run the tests, use:
+```bash
+python -m pytest --pyargs dpnp
+```

dpnp/backend/kernels/dpnp_krnl_common.cpp

@@ -33,11 +33,23 @@
 #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>
@@ -76,8 +88,13 @@ 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]) *

tests/third_party/cupy/creation_tests/test_ranges.py

@@ -172,7 +172,7 @@ def test_linspace_float_overflow(self, xp):
         dtype = cupy.default_float_type()
         return xp.linspace(0.0, xp.finfo(dtype).max / 5, 10, dtype=dtype)
 
-    @testing.numpy_cupy_allclose()
+    @testing.numpy_cupy_allclose(rtol={numpy.float32: 1e-6, "default": 1e-7})
     def test_linspace_float_underflow(self, xp):
         # find minimum subnormal number
         dtype = cupy.default_float_type()