tag | d93483904c2bc84e4a072c6a4bc568ff5f9d6539 | |
---|---|---|
tagger | The Android Open Source Project <initial-contribution@android.com> | Thu Dec 07 00:36:46 2023 -0800 |
object | d841e6d5645cd3678eeb54ceaad1e76d2d8671ca |
aml_mpr_341111020 (10992385,com.google.android.mediaprovider)
commit | d841e6d5645cd3678eeb54ceaad1e76d2d8671ca | [log] [tgz] |
---|---|---|
author | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sun Aug 06 21:43:28 2023 +0000 |
committer | Android Build Coastguard Worker <android-build-coastguard-worker@google.com> | Sun Aug 06 21:43:28 2023 +0000 |
tree | dafe91a2743a7199a21eb64a289f360b89552bf6 | |
parent | 76743d156a11ae8142de409d85a4e6ec0ffc7ff4 [diff] | |
parent | b5f0fa5e651724699c4b4ff204d9b04e8efb071f [diff] |
Snap for 10618552 from b5f0fa5e651724699c4b4ff204d9b04e8efb071f to mainline-mediaprovider-release Change-Id: I76b23df48c36c416579c780ed0d167b63f2951dd
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.