Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPU
Version: 2.2.0
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. Trademarks & copyright
Optimising Temporary Memory Usage for Convolutions and Matmuls on the IPU
Index