| commit | c165d6b0f1a1be9ddd2f904e8f87a4c1d9b38c43 | [log] [tgz] |
|---|---|---|
| author | Sadaf Ebrahimi <sadafebrahimi@google.com> | Mon Nov 11 19:00:29 2024 +0000 |
| committer | Automerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com> | Mon Nov 11 19:00:29 2024 +0000 |
| tree | f6eb22a741dd21439da987fb2c996e39e061b292 | |
| parent | 50531cb2052b4083c38413a4263402724e66bd96 [diff] | |
| parent | 1b6b89384074ec92f58e83f85ddae921138a1db2 [diff] |
Upgrade ruy to c08ec529fc91722bde519628d9449258082eb847 am: 898c7d70e1 am: 1b6b893840 Original change: undetermined Change-Id: Ie55a0f02d11ac87d6c8a6ca7f9d2d103a7b807b7 Signed-off-by: Automerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com>
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.