The following Graphcore documents are available.
Information on how to install the drivers and other essential software for your IPU-Server, how to run your first IPU program and get started with TensorFlow and PopART.
An overview of all the components of the Poplar SDK, and how you can download and install it.
An introduction to the IPU architecture, programming model and tools available.
A set of pre-built Docker packages containing components of the Poplar SDK.
TensorFlow for the IPU¶
Running TensorFlow on the IPU.
The Poplar Advanced Runtime (PopART) for importing and executing models from industry standard ML frameworks, using the ONNX format.
Poplar graph programming framework¶
The Poplar graph programming framework.
Information on how to use the Poplar graph programming tools to write code for the IPU.
Details of the functions in the Poplar and PopLibs libraries provided in the Poplar SDK.
An introduction to programming in assembly language on the IPU. This also includes some useful detail about memory layout and usage by the Poplar tools.
A detailed description of the file formats used for Poplar profiling information.
Technical notes provide more detailed information on some specific aspect of Graphcore technology.
A technical note that explains the process of porting your TensorFlow application to the IPU.
A technical note describing ways of exploiting the parallelism of the IPUs for your TensorFlow application.
Describes the contents of the files created by the Poplar tools with static and runtime profiling information. These files are mainly intended for use by the PopVision Graph Analyser but this may be useful to people wanting to use the data for their own purposes.
Low-level command line tools for managing IPU hardware.
Commands for controlling and monitoring the status of the IPUs in your systems.
Open source software¶
The following software is available as open source:
TensorFlow for the IPU
Poprithms: a library of graph algorithms used by the ML frameworks.
PopLibs, PopART and Poprithms are licensed under the terms of the MIT license.
TensorFlow for the IPU is licensed under the Apache License 2.0.