From 4c868cc909622c2f8efdece00500fd0c05fec140 Mon Sep 17 00:00:00 2001 From: Aleksandr Voron Date: Thu, 5 Oct 2023 10:08:43 +0200 Subject: [PATCH] [CPU][ARM][DOC] ARM documentation - 23.1 release (#19464) * arm docs * Update docs/OV_Runtime_UG/supported_plugins/CPU.md Co-authored-by: Tatiana Savina * Update docs/OV_Runtime_UG/supported_plugins/CPU.md Co-authored-by: Tatiana Savina * remove f16 * add space * update plugin link --------- Co-authored-by: Tatiana Savina --- README.md | 6 +++--- docs/OV_Runtime_UG/supported_plugins/CPU.md | 2 +- .../supported_plugins/Device_Plugins.md | 1 + docs/dev/build_windows.md | 12 ------------ docs/resources/Supported_Devices.md | 2 +- 5 files changed, 6 insertions(+), 17 deletions(-) diff --git a/README.md b/README.md index 2b51e65381f..65a2a347bf6 100644 --- a/README.md +++ b/README.md @@ -73,9 +73,9 @@ The OpenVINO™ Runtime can infer models on different hardware devices. This sec Intel Xeon with Intel® Advanced Vector Extensions 2 (Intel® AVX2), Intel® Advanced Vector Extensions 512 (Intel® AVX-512), and AVX512_BF16, Intel Core Processors with Intel AVX2, Intel Atom Processors with Intel® Streaming SIMD Extensions (Intel® SSE) - ARM CPU - openvino_arm_cpu_plugin - Raspberry Pi™ 4 Model B, Apple® Mac mini with M1 chip, NVIDIA® Jetson Nano™, Android™ devices + ARM CPU + openvino_arm_cpu_plugin + Raspberry Pi™ 4 Model B, Apple® Mac with Apple silicon GPU diff --git a/docs/OV_Runtime_UG/supported_plugins/CPU.md b/docs/OV_Runtime_UG/supported_plugins/CPU.md index 04ecd9b2222..320cec2583e 100644 --- a/docs/OV_Runtime_UG/supported_plugins/CPU.md +++ b/docs/OV_Runtime_UG/supported_plugins/CPU.md @@ -52,7 +52,7 @@ CPU plugin supports the following data types as inference precision of internal - Floating-point data types: - ``f32`` (Intel® x86-64, Arm®) - - ``bf16``(Intel® x86-64) + - ``bf16`` (Intel® x86-64) - Integer data types: - ``i32`` (Intel® x86-64, Arm®) diff --git a/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md b/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md index 53778ab9b7f..3849109927c 100644 --- a/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md +++ b/docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md @@ -24,6 +24,7 @@ OpenVINO™ Runtime can infer deep learning models using the following device ty * :doc:`CPU ` * :doc:`GPU ` * :doc:`GNA ` +* :doc:`Arm® CPU ` For a more detailed list of hardware, see :doc:`Supported Devices `. diff --git a/docs/dev/build_windows.md b/docs/dev/build_windows.md index 63dce5780cc..f63617a45b0 100644 --- a/docs/dev/build_windows.md +++ b/docs/dev/build_windows.md @@ -27,12 +27,6 @@ Supported configurations: cd openvino git submodule update --init --recursive ``` - (Extra for WoA) To build on Windows on ARM with ARM plugin: - ```sh - git clone https://github.com/openvinotoolkit/openvino_contrib.git - cd openvino_contrib - git submodule update --init --recursive - ``` 2. Create build directory: ```sh @@ -40,16 +34,10 @@ Supported configurations: ``` 3. In the `build` directory, run `cmake` to fetch project dependencies and generate a Visual Studio solution. - On Windows x86 64-bits: ```sh cmake -G "Visual Studio 16 2019" -DCMAKE_BUILD_TYPE=Release ``` - On Windows on ARM for ARM64 architecture: - ```sh - cmake -G "Visual Studio 16 2019" -DOPENVINO_EXTRA_MODULES=/modules/arm_plugin -DCMAKE_BUILD_TYPE=Release - ``` - 4. Build generated solution in Visual Studio or run `cmake --build . --config Release --verbose -j8` to build from the command line. Be aware that this process may take some time. 5. Before running the samples, add paths to the Threading Building Blocks (TBB) binaries used for the build to the `%PATH%` environment variable. By default, TBB binaries are downloaded by the CMake-based script to the `/temp/tbb/bin` folder. diff --git a/docs/resources/Supported_Devices.md b/docs/resources/Supported_Devices.md index 8f4f1833914..768a80df220 100644 --- a/docs/resources/Supported_Devices.md +++ b/docs/resources/Supported_Devices.md @@ -30,7 +30,7 @@ Currently, processors of the 11th generation and later (up to the 13th generatio || | Intel® Core™ Processors with Intel® AVX2, | || | Intel® Atom® Processors with Intel® Streaming SIMD Extensions (Intel® SSE) | || | | -|| (Arm®) | Raspberry Pi™ 4 Model B, Apple® Mac mini with M1 chip, NVIDIA® Jetson Nano™, Android™ devices | +|| (Arm®) | Raspberry Pi™ 4 Model B, Apple® Mac with Apple silicon | || | | +---------------------------------------------------------------------+------------------------------------------------------------------------------------------------------+ || :doc:`GPU ` | Intel® Processor Graphics including Intel® HD Graphics and Intel® Iris® Graphics, |