5. Next steps

For more information about working with PyTorch on IPUs refer to the following:

• Documentation

  • The IPU Programmer’s Guide provides an introduction to the IPU architecture, programming model and tools available.

  • User guide and API reference for running PyTorch on the IPU.

  • Technical notes covering a range of topics for optimising models for the IPU.

• Tutorials and simple examples

  All tutorials are available from https://github.com/graphcore/tutorials.

  Note

  You need to checkout the branch of the tutorials repository that corresponds to the version of the Poplar SDK you are using. The links below link to the master branch, which is the same the latest release branch.

  • Tutorials for PyTorch.

  • Simple applications for PyTorch.

  • Feature examples for PyTorch.

• Application and code examples

  • All examples are available from https://github.com/graphcore/examples.

  Note

  You need to checkout the branch of the examples repository that corresponds to the version of the Poplar SDK you are using. The links below link to the master branch, which is the same the latest release branch.

  • Browse the Graphcore Model Garden. You can filter by model type and framework.

  • There are other examples of models in the Examples repository. These include commonly-used machine learning models for training and inference.

• When looking for answers or asking questions on StackOverflow, use the tag “ipu”. For framework-specific questions, add the corresponding tag: “poplar”, “pytorch” and “popart”.

• You can request support from the Product Support team on the Graphcore Support portal by clicking on the Submit a ticket link.