tag | 4ce88465c7e666ae9e6bace413ab793c91096a19 | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Mon Aug 22 14:00:16 2022 -0700 |
object | 194105c4b9abb9b9af9c94f58246462f8a395bb7 |
Platform Tools Release 33.0.2 (8557947)
commit | 194105c4b9abb9b9af9c94f58246462f8a395bb7 | [log] [tgz] |
---|---|---|
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sun May 08 04:34:53 2022 +0000 |
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sun May 08 04:34:53 2022 +0000 |
tree | 81d7508721085bfb6debe2539a2ca5c385298795 | |
parent | 8421b3826629c0f6ba4732005d977244592951bb [diff] | |
parent | 4377b97cf0850e0a61caa191586ebe68ccbc2abf [diff] |
Snap for 8554636 from 4377b97cf0850e0a61caa191586ebe68ccbc2abf to sdk-release Change-Id: Ic8eb0edd78e302dec04cdffde65d7836657e5008
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.