commit | 52c5b21f66eb658d714c72e93cf3b54e9f0c624b | [log] [tgz] |
---|---|---|
author | Raman Tenneti <rtenneti@google.com> | Mon Sep 20 07:59:22 2021 +0000 |
committer | Automerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com> | Mon Sep 20 07:59:22 2021 +0000 |
tree | 81d7508721085bfb6debe2539a2ca5c385298795 | |
parent | d4ddc68d70a2a5d9006ec93f1927819baea347be [diff] | |
parent | fcc4bc8baf6c6f7d0ed1f4b035fd38ad5c22da0e [diff] |
Remove external/ruy/.gitmodules and submodule directories. am: 8931679bde am: 683842157f am: fcc4bc8baf Original change: https://android-review.googlesource.com/c/platform/external/ruy/+/1830441 Change-Id: I0fa11e2591dcda9c716ff1226657d18b3a4bdd77
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.