commit | 35891dbbfa6490e3b6f7971483604c228df4da78 | [log] [tgz] |
---|---|---|
author | Lev Proleev <levp@google.com> | Fri Feb 26 22:04:42 2021 +0000 |
committer | Lev Proleev <levp@google.com> | Fri Feb 26 22:35:20 2021 +0000 |
tree | 3205fa4f087c9bf433c259269313fc25c821a0ee | |
parent | 713d254ecfa1f658e77ad93898d34caafcdff698 [diff] |
Add Android.bp to ruy project Ruy was a part of TF Lite but now migrated into a separate library Bug: 178609672 Test: mma Change-Id: If7c782ba236df5dc8b16846f5d6ec71bdc5c54f4
This is not an officially supported Google product.
ruy is a matrix multiplication library. Its focus is to cover the matrix multiplication needs of neural network inference engines. Its initial user has been TensorFlow Lite, where it is used by default on the ARM CPU architecture.
ruy supports both floating-point and 8bit-integer-quantized matrices.
ruy is designed to achieve high performance not just on very large sizes, as is the focus of many established libraries, but on whatever are the actual sizes and shapes of matrices most critical in current TensorFlow Lite applications. This often means quite small sizes, e.g. 100x100 or even 50x50, and all sorts of rectangular shapes. It's not as fast as completely specialized code for each shape, but it aims to offer a good compromise of speed across all shapes and a small binary size.
Some documentation will eventually be available in the doc/ directory, see doc/README.md.