Software Documents¶
Licensed Software
This software is made available under the terms of the Graphcore End User License Agreement (EULA). Please ensure you have read and accept the terms of the license before using the software.
Release notes for each software release can be found on the Graphcore software download site.
TensorFlow¶
User guides and API reference for the IPU implementation of TensorFlow and Keras.
PopART¶
The Poplar Advanced Runtime (PopART) for importing and executing models from industry standard ML frameworks, using the ONNX format.
Poplar Graph Programming Framework¶
Information on how to use the Poplar graph programming tools to write code for the IPU.
Poplar and PopLibs API Reference
Details of the functions in the Poplar and PopLibs libraries provided in the Poplar SDK.
Vertex Assembly Programming Guide
Information about programming in vertices on the IPU. This also includes some useful detail about memory layout, programming in assembly language and interfaces to other tools.
Technical Notes¶
Creating Custom Operations for the IPU
Adding custom operations to PyTorch, TensorFlow and PopART.
Porting TensorFlow models to the IPU
A summary of the process of porting your TensorFlow application to the IPU.
Model parallelism with TensorFlow: sharding and pipelining
Exploiting the parallelism of the IPUs for your TensorFlow application.
Optimising for the IPU: Computational Graph Recompilation and Executable Switching in TensorFlow
Tips for managing graph compilation in TensorFlow.
Pre-Training and Fine-Tuning BERT for the IPU
A description of the implementation and performance of BERT-Large on Graphcore IPU-POD systems.
Profiling and Debugging¶
The documentation for the PopVision Graph Analyser and System Analyser. This information is also available as context-sensitive help in the tools.
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 user’s wanting to understand the data for their own purposes or tool development.
Open Source Software¶
The following software is available as open source:
TensorFlow for the IPU
PopTorch
PopART
PopLibs libraries
Poprithms: a library of graph algorithms used by the ML frameworks.
See also the Examples and Tutorials.
License Agreements¶
Graphcore End User License Agreement (EULA)
PopLibs, PopTorch, PopART and Poprithms are licensed under the terms of the MIT license
TensorFlow for the IPU is licensed under the Apache License 2.0
Open source Contribution License Agreement (CLA)