From 3ed70c005559d409feff2c578a1a39cf8fec8804 Mon Sep 17 00:00:00 2001 From: Colm Donelan Date: Tue, 12 Nov 2024 16:19:49 +0000 Subject: [PATCH] Updating documentation to remove references to the pre-built AAR. The pre-built AAR binary will not be released in 24.11. This patch removes references to it from the documentation. Signed-off-by: Colm Donelan Change-Id: Ia773dbb96af3f5c0061fb73ccc04f3974f25d2f7 --- README.md | 28 +++++++++------------------- delegate/armnnDelegateJNI/README.md | 7 ------- 2 files changed, 9 insertions(+), 26 deletions(-) diff --git a/README.md b/README.md index 6459cb3e06..d0fbfc36f5 100644 --- a/README.md +++ b/README.md @@ -38,14 +38,7 @@ Delegate and run accelerated inference. Please see this **[Arm Developer Guide](https://developer.arm.com/documentation/102561/latest/)** for information on how to accelerate your TF Lite model using the Arm NN TF Lite Delegate. -The fastest way to integrate Arm NN into an **Android app** is by using our **Arm NN AAR (Android Archive) file with -Android Studio**. The AAR file nicely packages up the Arm NN TF Lite Delegate, Arm NN itself and ACL; ready to be -integrated into your Android ML application. Using the AAR allows you to benefit from the **vast operator support** of -the Arm NN TF Lite Delegate. We held an **[Arm AI Tech Talk](https://www.youtube.com/watch?v=Zu4v0nqq2FA)** on how to -accelerate an ML Image Segmentation app in 5 minutes using this AAR file. To download the Arm NN AAR file, please see the -**[Pre-Built Binaries](#pre-built-binaries)** section below. - -We also provide Debian packages for Arm NN, which are a quick way to start using Arm NN and the TF Lite Parser +We provide Debian packages for Arm NN, which are a quick way to start using Arm NN and the TF Lite Parser (albeit with less ML operator support than the TF Lite Delegate). There is an installation guide available [here](InstallationViaAptRepository.md) which provides instructions on how to install the Arm NN Core and the TF Lite Parser for Ubuntu 20.04. @@ -61,11 +54,10 @@ Arm NN from scratch is the ability to **exactly choose which components to build | Operating System | Architecture-specific Release Archive (Download) | |-----------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| Android (AAR) | [![](https://img.shields.io/badge/download-android--aar-green)](https://github.com/ARM-software/armnn/releases/download/v24.08/armnn_delegate_jni-24.08.aar) | -| Android 11 "R/Red Velvet Cake" (API level 30) | [![](https://img.shields.io/badge/download-arm64--v82a-orange)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-30-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v8a-orange)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-30-arm64-v8a.tar.gz) | -| Android 12 "S/Snow Cone" (API level 31) | [![](https://img.shields.io/badge/download-arm64--v82a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-31-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v8a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-31-arm64-v8a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-31-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-31-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-31-arm64-v8.6-a-sve2.tar.gz) | -| Android 13 "T/Tiramisu" (API level 33) | [![](https://img.shields.io/badge/download-arm64--v82a-purple)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-33-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-purple)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-33-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-purple)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-33-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-purple)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-33-arm64-v8.6-a-sve2.tar.gz) | -| Android 14 "U/Upside Down Cake" (API level 34)| [![](https://img.shields.io/badge/download-arm64--v82a-blue)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-34-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-blue)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-34-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-blue)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-34-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-blue)](https://github.com/ARM-software/armnn/releases/download/v24.08/ArmNN-android-34-arm64-v8.6-a-sve2.tar.gz) | +| Android 11 "R/Red Velvet Cake" (API level 30) | [![](https://img.shields.io/badge/download-arm64--v82a-orange)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-30-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v8a-orange)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-30-arm64-v8a.tar.gz) | +| Android 12 "S/Snow Cone" (API level 31) | [![](https://img.shields.io/badge/download-arm64--v82a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-31-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v8a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-31-arm64-v8a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-31-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-31-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-yellow)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-31-arm64-v8.6-a-sve2.tar.gz) | +| Android 13 "T/Tiramisu" (API level 33) | [![](https://img.shields.io/badge/download-arm64--v82a-purple)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-33-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-purple)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-33-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-purple)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-33-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-purple)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-33-arm64-v8.6-a-sve2.tar.gz) | +| Android 14 "U/Upside Down Cake" (API level 34)| [![](https://img.shields.io/badge/download-arm64--v82a-blue)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-34-arm64-v8.2-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86a-blue)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-34-arm64-v8.6-a.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve-blue)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-34-arm64-v8.6-a-sve.tar.gz) [![](https://img.shields.io/badge/download-arm64--v86asve2-blue)](https://github.com/ARM-software/armnn/releases/download/v24.11/ArmNN-android-34-arm64-v8.6-a-sve2.tar.gz) | Arm NN also provides pre-built multi-isa binaries for Android. The v8a binary includes support from basic v8a architecture and upwards. The v8.2a binary includes support from v8.2a and upwards. These include support for SVE, SVE2, FP16 and some dot product kernels. @@ -74,10 +66,10 @@ These kernels need appropriate hardware to work on. | Multi ISA Architecture | Release Archive (Download) | |------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| -| Linux Arm v8a | [![](https://img.shields.io/badge/download-arm64--v8a-pink)](https://github.com/ARM-software/armnn/releases/download/v24.08/MULTI_ISA-GCC11-ArmNN+ACL-linux-armv8a.tar.gz) | -| Linux Arm v8.2a | [![](https://img.shields.io/badge/download-arm64--v82a-violet)](https://github.com/ARM-software/armnn/releases/download/v24.08/MULTI_ISA-GCC11-ArmNN+ACL-linux-armv8.2-a.tar.gz) | -| Android 31 v8a | [![](https://img.shields.io/badge/download-android--v8a-tan)](https://github.com/ARM-software/armnn/releases/download/v24.08/MULTI_ISA-ArmNN+ACL+SL-android-31-arm64-v8a.tar.gz) | -| Android 31 v8.2a | [![](https://img.shields.io/badge/download-android--v82a-indigo)](https://github.com/ARM-software/armnn/releases/download/v24.08/MULTI_ISA-ArmNN+ACL+SL-android-31-arm64-v8.2-a.tar.gz) | +| Linux Arm v8a | [![](https://img.shields.io/badge/download-arm64--v8a-pink)](https://github.com/ARM-software/armnn/releases/download/v24.11/MULTI_ISA-GCC11-ArmNN+ACL-linux-armv8a.tar.gz) | +| Linux Arm v8.2a | [![](https://img.shields.io/badge/download-arm64--v82a-violet)](https://github.com/ARM-software/armnn/releases/download/v24.11/MULTI_ISA-GCC11-ArmNN+ACL-linux-armv8.2-a.tar.gz) | +| Android 31 v8a | [![](https://img.shields.io/badge/download-android--v8a-tan)](https://github.com/ARM-software/armnn/releases/download/v24.11/MULTI_ISA-ArmNN+ACL+SL-android-31-arm64-v8a.tar.gz) | +| Android 31 v8.2a | [![](https://img.shields.io/badge/download-android--v82a-indigo)](https://github.com/ARM-software/armnn/releases/download/v24.11/MULTI_ISA-ArmNN+ACL+SL-android-31-arm64-v8.2-a.tar.gz) | @@ -95,8 +87,6 @@ into your ML application. Please note that these parsers do not provide extensiv to the Arm NN TF Lite Delegate. **Android** ML application developers have a number of options for using Arm NN: -* Use our Arm NN AAR (Android Archive) file with **Android Studio** as described in the -[Quick Start Guides](#quick-start-guides) section * Download and use our [Pre-Built Binaries](#pre-built-binaries) for the Android platform * Build Arm NN from scratch with the Android NDK using this [GitHub guide](BuildGuideAndroidNDK.md) diff --git a/delegate/armnnDelegateJNI/README.md b/delegate/armnnDelegateJNI/README.md index 98ddd54a34..9bbe90b74c 100644 --- a/delegate/armnnDelegateJNI/README.md +++ b/delegate/armnnDelegateJNI/README.md @@ -2,14 +2,7 @@ NOTE: This library is an experimental feature. We cannot guarentee full support for this. -'armnnDelegateJNI' is a library for accelerating certain TensorFlow Lite operators on Arm hardware specifically through Android -applications. Each release is packaged in an AAR which can be found on Maven Central. -The pre-built library contains the ArmNN Core, ArmNN Utils, Neon backend, CL Backend, and the ArmNN Delegate. -It is essential to only build these. The backends you choose are optional. - It requires a static build which can be switched on through setting BUILD_SHARED_LIBS=OFF. You will also have to set CMAKE_ANDROID_STL_TYPE=c++_static when building ArmNN. BUILD_DELEGATE_JNI_INTERFACE will also have to be set to true. - -To download the prebuilt ArmNN Delegate JNI AAR from Maven Central, please go to [ArmNN Maven Central Release Page](https://search.maven.org/artifact/io.github.arm-software/armnn.delegate).