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
  • 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
  • »
  • Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPU
  • Edit on GitHub

Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPUΒΆ

  • 1. Introduction to the available memory proportion option
    • 1.1. The convolution planner
  • 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
Next

Revision 4562bcf1.

Read the Docs v: latest
Versions
latest
2.4.0
2.3.0
2.2.0
2.1.0
1.0.0
preview_heatmap
Downloads
pdf
On Read the Docs
Project Home
Builds