The Intel® Python DPNP Getting Started sample code shows how to find conjugate gradient using the Intel Python API powered by the Intel® Python DPNP - Data Parallel Extension for NumPy.
| Area | Description |
|---|---|
| Category | Getting Started |
| What you will learn | DPNP programming model for Intel GPU |
| Time to complete | 60 minutes |
Note: This sample is migrated from Cupy Python sample. See the ConjugateGradient sample in the cupy-samples GitHub.
The Data Parallel Extension for NumPy* (dpnp package) - a 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.
The DPNP is used to offload python code to INTEL GPU's. This is very similar to CUPY API Comparsion_list.
| Optimized for | Description |
|---|---|
| OS | Ubuntu* 22.04 (or newer) |
| Hardware | Intel® Gen9 Intel® Gen11 Intel® Data Center GPU Max |
| Software | Intel® Python Data Parallel Extension for NumPy (DPNP) |
Note: Intel® Python DPNP - Data Parallel Extension for NumPy.
- This get-started sample code is implemented for Intel GPUs using Python language. The example assumes the user has the latest DPNP installed in the environment, similar to what is delivered with the installation of the Intel® Distribution for Python*.
You will need to download and install the following toolkits, tools, and components to use the sample.
1. Intel Python
Required Intel Python package: DPNP (Select Intel® Distribution for Python*: Offline on Get Intel® Distribution for Python* to install)
2. (Offline Installer) Update the Intel Python base environment
Load python env:
source $PYTHON_INSTALL/env/vars.sh
3. (Offline Installer) Check the DPNP version
python -c "import dpnp; print(dpnp.__version__)"
Note: if the version is 0.15.0 or more continue, otherwise need to upgrade the dpnp version
4. Clone the GitHub repository
git clone https://github.com/oneapi-src/oneAPI-samples.git
cd oneAPI-samples/DirectProgramming/Python/DPNP_GettingStarted
Note: Before running the sample, make sure Intel Python is installed.
- Change to the sample directory.
- Build the program.
$ python cg.py
Code samples are licensed under the MIT license. See License.txt for details.
Third party program Licenses can be found here: third-party-programs.txt
*Other names and brands may be claimed as the property of others. Trademarks