History

hcl 7be3fd486c init from android-12.1.0_r8		2023-01-09 17:11:35 +08:00
..
cmake	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
doc	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
example	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
ruy	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
third_party	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
.gitignore	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
.gitmodules	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
Android.bp	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
BUILD	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
CMakeLists.txt	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
CONTRIBUTING.md	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
LICENSE	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
README.md	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00
WORKSPACE	init from android-12.1.0_r8	2023-01-09 17:11:35 +08:00

README.md

The ruy matrix multiplication library

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.

Efficiency

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.

Documentation

Some documentation will eventually be available in the doc/ directory, see doc/README.md.