Low-memory GEMM-based convolution algorithms for deep neural networks

no code implementations • 8 Sep 2017 • Andrew Anderson, Aravind Vasudevan, Cormac Keane, David Gregg

We present two novel GEMM-based algorithms that require just $O(MHW)$ and $O(KW)$ additional space respectively, where $M$ is the number of channels in the result of the convolution.