Logo
Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPU
Version: latest
  • 1. Introduction to the available memory proportion option
    • 1.1. The convolution planner
    • 1.2. Setting availableMemoryProportion to a very small value
  • 2. Worked example
    • 2.1. Use case 1: fitting a model or pipeline stage
    • 2.2. Use case 2: Optimising for throughput
  • 3. How to set the available memory proportion
    • 3.1. TensorFlow
    • 3.2. PyTorch
    • 3.3. PopART
  • 4. Legal notices
Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPU

4. Legal notices

Graphcloud®, Graphcore®, Poplar® and PopVision® are registered trademarks of Graphcore Ltd.

Bow™, Bow-2000™, Bow Pod™, Colossus™, In-Processor-Memory™, IPU-Core™, IPU-Exchange™, IPU-Fabric™, IPU-Link™, IPU-M2000™, IPU-Machine™, IPU-POD™, IPU-Tile™, PopART™, PopDist™, PopLibs™, PopRun™, PopTorch™, Streaming Memory™ and Virtual-IPU™ are trademarks of Graphcore Ltd.

All other trademarks are the property of their respective owners.

Copyright © 2021 Graphcore Ltd. All rights reserved.

Previous

Revision 4cea98e6.

Read the Docs v: latest