commit | fae850ec1f3b7529474a19ece429d4addf9772ef | [log] [tgz] |
---|---|---|
author | Xin Li <delphij@google.com> | Mon Apr 29 11:50:52 2024 -0700 |
committer | Xin Li <delphij@google.com> | Mon Apr 29 11:50:52 2024 -0700 |
tree | 8e9ad84e9f0e111f0b67522627a9034074223408 | |
parent | 127564d6e645c2bdefe2ff410e8a26a67df587c9 [diff] | |
parent | 9683dfe27d44c8dc053612d488f83f1b413ebb4c [diff] |
Empty merge of Android 24Q2 Release (ab/11526283) to aosp-main-future Bug: 337098550 Merged-In: I31f8668b6226f888097e9dd41f0a4eb7cf570437 Change-Id: Ied2360000506264b6ef6b40c18b34ee971c9fcd8
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.