tag | 1ddc9b29aebada46bb6a11fa1d3258622e935c65 | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Tue Aug 02 10:53:34 2022 -0700 |
object | 95b5bb2250cb983a08f6fdd088b018045bf1da41 |
Android 12.1.0 release 20
commit | 95b5bb2250cb983a08f6fdd088b018045bf1da41 | [log] [tgz] |
---|---|---|
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sat Feb 05 02:05:31 2022 +0000 |
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sat Feb 05 02:05:31 2022 +0000 |
tree | 420dd314b49b6a7f5772ae3cb6e5f738520572b8 | |
parent | 033350c4252004f65e85e8d547b473ae28ebd158 [diff] | |
parent | 380f85132f1641c8792107342183fc3e44eca2fa [diff] |
Snap for 8150059 from 380f85132f1641c8792107342183fc3e44eca2fa to sc-qpr3-release Change-Id: I90338c24ed3bd21881292b4f8c0ce75123f62c5b
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.