| tag | 97930a4050fe403333100742b0f9b456f0b66383 | |
|---|---|---|
| tagger | The Android Open Source Project <initial-contribution@android.com> | Tue May 07 10:57:58 2024 -0700 |
| object | facbc89572a4041a616e71d8da319985487b135d |
Android 14.0.0 release 36
| commit | facbc89572a4041a616e71d8da319985487b135d | [log] [tgz] |
|---|---|---|
| author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sat Oct 07 23:17:06 2023 +0000 |
| committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sat Oct 07 23:17:06 2023 +0000 |
| tree | 8e9ad84e9f0e111f0b67522627a9034074223408 | |
| parent | d60f8b504c2b08c1c891b23808c12285e5938b4e [diff] | |
| parent | 609678b294bb9a69fd101c77a26586656e9df541 [diff] |
Snap for 10917888 from 609678b294bb9a69fd101c77a26586656e9df541 to 24Q1-release Change-Id: I0403f6145ae2648e4bd228f23074729f3997684a
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.