Eigen Tensor library for convolutions on CPU #22550
Labels
function request
A request for a new function or the addition of new arguments/modes to an existing function.
module: arm
Related to ARM architectures builds of PyTorch. Includes Apple M1
module: convolution
Problems related to convolutions (THNN, THCUNN, CuDNN)
module: cpu
CPU specific problem (e.g., perf, algorithm)
module: performance
Issues related to performance, either of kernel code or framework glue
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
馃殌 Feature
Add option of Eigen Tensor library implementation of convolution on ARM CPU
Motivation
While convolutions on Intel CPUs are quite fast, there are issues on ARM processors. I tried NNPack which speeds up the default implementation. However TensorFlow is much faster on Raspberry, and also NNabla. The underlying library is Eigen Tensor library which often is even better than ARM compute library.
cc @VitalyFedyunin @ngimel @mruberry
The text was updated successfully, but these errors were encountered: