| commit | 32dd2b92622102b1309754ac5aa61c1a581dd194 | [log] [tgz] |
|---|---|---|
| author | davidbienvenu <bienvenu@davidbienvenu.org> | Tue Jul 25 18:51:45 2023 -0700 |
| committer | Copybara-Service <copybara-worker@google.com> | Tue Jul 25 18:52:07 2023 -0700 |
| tree | 320f39e50c425f68a6756c5af1071bd0d85f00be | |
| parent | da1f78712f7afd5ad4273562b429866601d74cfb [diff] |
handle null cpuinfo_get_arch The Arm64 Windows implementation of cpuinfo returns null from cpuinfo_get_uarch if it doesn't recognize the CPU, instead of a default cpuinfo_uarch_info, as it does for other cpu's. This PR makes ruy not crash when that happens. Closes https://github.com/google/ruy/pull/340 COPYBARA_INTEGRATE_REVIEW=https://github.com/google/ruy/pull/340 from davidbienvenu:fix_null_cpu_arch e2acd12b8de672bacc5298fb8c5e7982186dd2e0 PiperOrigin-RevId: 551059692
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.