4. Next steps

This page lists sources of information to help you learn about programming for, and running code on, the IPU.

4.1. Documentation

All documentation is on the Graphcore documentation portal. There you can find user guides for hardware and software, API references and technical notes.

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

Switching from GPUs to IPUs for Machine Learning Models provides a high-level overview of the programming changes required when switching from GPUs to IPUs.

Technical notes cover a range of topics about implementing and optimising models for the IPU.

4.2. Running applications in Docker

You can run Poplar applications in Docker on a Linux machine using one or more physical IPU devices.

Refer to Using IPUs from Docker for more information.

4.3. Running applications in Paperspace

You can use VS Code to run Poplar applications on Paperspace with the setup described in the notebook Using VS Code in Paperspace Notebooks.

4.4. Tutorials, examples and applications

You can browse the Graphcore Model Garden to find applications that run on IPUs. You can filter by category, model type and framework.

There are more applications in the examples repository on GitHub.

The latest tutorials and simple code examples are also in the examples repository:

Note

If you are using a version of the Poplar SDK prior to version 3.2, then refer to Section A, Install examples and tutorials for older Poplar SDK versions for how to install examples and tutorials.

4.5. Other support

  • When looking for answers or asking questions on StackOverflow, use the tag “ipu”.

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

  • For general help, discussions and announcements, please join our Graphcore Slack Community.