commit | a28320aaf5fe2bd8a8aa9c777fc1264a9b49a14f | [log] [tgz] |
---|---|---|
author | Leslie-Fang <Leslie-Fang@users.noreply.github.com> | Thu Oct 15 20:55:54 2020 -0400 |
committer | Benoit Jacob <benoitjacob@google.com> | Thu Oct 15 23:04:38 2020 -0400 |
tree | 3c6d44c8af5d03d4ce98c335361a3290e3862ea6 | |
parent | 034c0e2fc805e8bea53d47351da429d7f57bccf2 [diff] |
move example.cc into one directory move the examples into one directory. (This is a commit by Leslie Fang <Leslie-Fang@users.noreply.github.com> with a minor fixup) Closes https://github.com/google/ruy/pull/209 COPYBARA_INTEGRATE_REVIEW=https://github.com/google/ruy/pull/209 from Leslie-Fang:lesliefang/refactor_example 0c54c7e196abb0a3914ca2974efe99e3eb616065 PiperOrigin-RevId: 337420160
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.