4. Next steps

Full documentation for the Poplar software is available on the Graphcore documentation site: https://docs.graphcore.ai/. More information can be found on the Graphcore developer pages: https://www.graphcore.ai/developer.

For an overview of the Poplar SDK and development tools, see the SDK Overview.

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

If you are interested in running TensorFlow on the IPU, there are user guides and API references for the IPU implementation of TensorFlow 1 and TensorFlow 2.

You can also run PyTorch on the IPU.

Graphcore also has GitHub repositories with further examples:

• https://github.com/graphcore/examples:

  • TensorFlow, PyTorch and PopART versions of commonly used machine learning models for training and inference, including CNNs such as ResNet, ResNeXt and EfficientNet

  • Training data for the above models

• https://github.com/graphcore/tutorials:

  • Tutorials

  • Examples of using Poplar and IPU features

  • Examples of simple models

  • Source code from videos, blogs and other documents

  • Benchmarks for performance testing of layer types on your IPU system

You can use the tags “ipu”, “poplar” and “popart” when asking questions or looking for answers on StackOverflow.

Support is available from the Graphcore customer engineering team via the Graphcore support portal.