From ebb91a2c662bf88218c3970fb253c61704c32f28 Mon Sep 17 00:00:00 2001 From: "ramy.elgammal@arm.com" Date: Thu, 10 Aug 2023 15:34:35 +0100 Subject: Update Readme for 23.08 Resolves: COMPMID-6179 Signed-off-by: ramy.elgammal@arm.com Change-Id: I202b0ad66cebfebe2a07766b068a211a7597f035 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10097 Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins Reviewed-by: SiCong Li Benchmark: Arm Jenkins --- docs/user_guide/introduction.dox | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'docs/user_guide') diff --git a/docs/user_guide/introduction.dox b/docs/user_guide/introduction.dox index be4f5c8605..094a4480a0 100644 --- a/docs/user_guide/introduction.dox +++ b/docs/user_guide/introduction.dox @@ -34,7 +34,7 @@ namespace arm_compute The Compute Library is a collection of low-level machine learning functions optimized for both Arm CPUs and GPUs using SIMD technologies. Several builds of the library are available using various configurations: - - OS: Linux, Android, macOS or bare metal. + - OS: Linux®, Android™, macOS or bare metal. - Architecture: armv7a (32bit) or armv8a (64bit). - Technology: Arm® Neon™ / OpenCL / Arm® Neon™ and OpenCL. - Debug / Asserts / Release: Use a build with asserts enabled to debug your application and enable extra validation. Once you are sure your application works as expected you can switch to a release build of the library for maximum performance. @@ -49,7 +49,7 @@ Several builds of the library are available using various configurations: Architecture Minimum Toolchain - Linux + Linux® armv7a gcc-linaro-6.3.1-2017.05-x86_64_arm-linux-gnueabihf @@ -61,11 +61,14 @@ Several builds of the library are available using various configurations: armv8.2-a-sve gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu - Android + Android™ armv8a NDK r20b armv8.2-a + + armv8.2-a-sve + NDK r23b macOS armv8.2-a @@ -86,13 +89,14 @@ In order to facilitate the work of the support team please provide the build inf For each release we provide some pre-built binaries of the library [here](https://github.com/ARM-software/ComputeLibrary/releases). These binaries have been built using the following toolchains: - - Linux armv7a: gcc-linaro-7.2.1-2017.11-x86_64_arm-linux-gnueabihf - - Linux armv8a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu - - Linux armv8.2-a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu - - Linux armv8.2-a (multi-ISA binary): gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu - - Linux armv8.2-a-sve: gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu - - Android armv8a: clang++ / libc++ NDK r20b - - Android armv8.2-a: clang++ / libc++ NDK r20b + - Linux® armv7a: gcc-linaro-7.2.1-2017.11-x86_64_arm-linux-gnueabihf + - Linux® armv8a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu + - Linux® armv8.2-a: gcc-linaro-7.2.1-2017.11-x86_64_aarch64-linux-gnu + - Linux® armv8.2-a (multi-ISA binary): gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu + - Linux® armv8.2-a-sve: gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu + - Android™ armv8a: clang++ / libc++ NDK r20b + - Android™ armv8.2-a: clang++ / libc++ NDK r20b + - Android™ armv8.2-a-sve: clang++ / libc++ NDK r23b @warning Make sure to use a compatible toolchain to build your application or you will get some std::bad_alloc errors at runtime. -- cgit v1.2.1