Google Git
Sign in
android / platform / external / ruy / refs/tags/android-13.0.0_r20
tag44ad28cbffb3c67499dc618f37c2f945f9f62b22
taggerThe Android Open Source Project <initial-contribution@android.com>Tue Jan 03 11:21:54 2023 -0800
object461c36507d8af5d938c8965dfc1c7581bf686707 
Android 13.0.0 release 20
commit461c36507d8af5d938c8965dfc1c7581bf686707[log] [tgz]
authorIan Hua <ianhua@google.com>Fri Feb 04 19:07:43 2022 +0000
committerAutomerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com>Fri Feb 04 19:07:43 2022 +0000
tree81d7508721085bfb6debe2539a2ca5c385298795
parentb74caf65109512df73da70fd415c99fd135e67fe [diff]
parentce41e9d6f046881c480a81705be1922ae02a3779 [diff]
[automerger skipped] [automerged blank] Merge remote-tracking branch 'aosp/upstream-master' to 'aosp/master' for external/ruy. 2p: 380f85132f am: ce41e9d6f0 -s ours

am skip reason: Merged-In I71df6832de5c6fb310e9c2c97cdf361fc9074e80 with SHA-1 0cdefb826c is already in history

Original change: https://googleplex-android-review.googlesource.com/c/platform/external/ruy/+/16774445

Change-Id: I52860e7e7e6a5d483491f095fe7affd6d450adea
tree: 81d7508721085bfb6debe2539a2ca5c385298795
  1. cmake/
  2. doc/
  3. example/
  4. ruy/
  5. third_party/
  6. .gitignore
  7. Android.bp
  8. BUILD
  9. CMakeLists.txt
  10. CONTRIBUTING.md
  11. LICENSE
  12. README.md
  13. WORKSPACE
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.