Logo
Targeting the IPU from TensorFlow
Version: 1.3.30
  • 1. Introduction
  • 2. Tutorial
  • 3. Targeting the Poplar XLA device
  • 4. Training a model
  • 5. Example using IPUEstimator
  • 6. Example using IPUPipelineEstimator
  • 7. Distributed training
  • 8. Half-precision floating point and stochastic rounding
  • 9. IPU-optimised operations
  • 10. IPU Functions
  • 11. Custom IPU operations
  • 12. IPU host embeddings
  • 13. Retrieving information about compilation and execution
  • 14. Python API
  • 15. TensorFlow operators supported by the IPU
  • 16. References
  • 17. Index
  • 18. Trademarks & copyright
Targeting the IPU from TensorFlow

18. Trademarks & copyright

Graphcore® and Poplar® are Registered Trademarks of Graphcore Ltd.

Colossus™, IPU-Core™, In-Processor-Memory™, Exchange Memory™, Streaming Memory™, IPU-Tile™, IPU-Exchange™, IPU-Machine™, IPU-POD™, IPU-Link™, Virtual-IPU™, AI-Float™, IPU-Fabric™ and PopVision™ are Trademarks of Graphcore Ltd.

All other trademarks are the property of their respective owners.

Copyright © 2016-2020 Graphcore Ltd. All rights reserved.

Previous

Revision b0b8fd7f.