tag | 089fda889abe4b679e3598daf434a563c269b32e | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Fri Sep 17 01:20:12 2021 -0700 |
object | 4fbb87cbe25a53e44160c93fe5512a1b411f6160 |
Platform Tools Release 31.0.3 (7562133)
commit | 4fbb87cbe25a53e44160c93fe5512a1b411f6160 | [log] [tgz] |
---|---|---|
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Thu Jun 24 04:46:22 2021 +0000 |
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Thu Jun 24 04:46:22 2021 +0000 |
tree | aa0ec83d43383d770e0db00bbaa4d59a16283304 | |
parent | 648fdfb2d39273a656d91af7c9c58614e1528171 [diff] | |
parent | 6332d3e7772feb974cdd5c174442f89bf69d80c0 [diff] |
Snap for 7487883 from 6332d3e7772feb974cdd5c174442f89bf69d80c0 to sdk-release Change-Id: Icdbbd1c93f652fd98c22750734e9ad94d771a100
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.