tag | d313641bff3739ea91dfc37791b2c8015a89c09d | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Sat Oct 01 12:38:19 2022 -0700 |
object | 1de3157eb8694fada78670f1dd102eb599cfc378 |
aml_go_per_330912000
commit | 1de3157eb8694fada78670f1dd102eb599cfc378 | [log] [tgz] |
---|---|---|
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Thu Jun 16 22:03:01 2022 +0000 |
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Thu Jun 16 22:03:01 2022 +0000 |
tree | 074d9d68a72f04f78ca88994b4c37daca1af2f6d | |
parent | 461c36507d8af5d938c8965dfc1c7581bf686707 [diff] | |
parent | f9af1b3f24d71678b7a7d33b652d114d9164d6a1 [diff] |
Snap for 8736029 from f9af1b3f24d71678b7a7d33b652d114d9164d6a1 to mainline-go-permission-release Change-Id: I8c4d04406370967e06e858b243eb390e874d8d20
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.