Data Parallel Control or dpctl is a Python* library that allows users to control the execution placement of a compute kernel on an XPU*.

The compute kernel can be a code:

• written by the user, e.g., using numba-dppy
• that is part of a library, such as oneMKL

The dpctl library is built upon the SYCL* standard. It also implements Python bindings for a subset of the standard runtime classes. Such classes allow users to:

• query platforms
• discover and represent devices and sub-devices
• construct contexts and queues

dpctl features classes for SYCL* Unified Shared Memory (USM) management and implements a tensor array API.

The library helps authors of Python native extensions written in C*, Cython*, or pybind11* to access dpctl objects representing SYCL* devices, queues, memory, and tensors.

Dpctl is the core part of a larger family of data-parallel Python* libraries and tools to program on XPUs.

You can install the library with conda* and pip*. It is also available in the Intel(R) Distribution for Python* (IDP).

You can find the most recent release of dpctl every quarter as part of the Intel(R) oneAPI releases.

To get the library from the latest oneAPI release, follow the instructions from Intel(R) oneAPI installation guide.

NOTE: You need to install the Intel(R) oneAPI Base Toolkit to get IDP and dpctl.

To install dpctl from the Intel(R) channel on Annaconda* cloud, use the following command:

conda install dpctl -c intel

To install dpctl from PyPi*, run the following command:

pip3 install dpctl

To try out the current master, install it from our development channel on Anaconda* cloud:

conda install dpctl -c dppy\label\dev

Refer to our Documentation for more information on setting up a development environment and building dpctl from the source.

Find our examples here.

To build these examples, run:

for script in `ls examples/python/`; 
    do echo "executing ${script}"; 
    python examples/python/${script}; 
done

See examples of building Cython* extensions with DPC++ compiler that interoperates with dpctl in the cython folder.

To build these examples, run:

CC=icx CXX=dpcpp python setup.py build_ext --inplace

To execute extensions, refer to the run.py script in each folder.

Tests are located here.

To run the tests, use:

pytest --pyargs dpctl