Merge branch 'ArmDeveloperEcosystem:main' into codex

Author: madeline-underwood

.wordlist.txt

@@ -5439,4 +5439,38 @@ snapshotter
 unmounting
 vnd
 xqcqqYHrjZ
-ztPjILBCbFEqnVlbvjUpM
+ztPjILBCbFEqnVlbvjUpM
+ArmKleidiAI
+DirectML
+DotProd
+GIMPLE
+GemV
+LinkTimeOptimization
+MIGraphX
+MLAS
+MLSA
+MOPA
+MTK
+MatMul
+MlasConv
+MlasDynamicQGemmBatch
+MlasGemmBatch
+Modescope
+Nascimento
+ParallemOpenMP
+Partitioner
+QNN
+SPECint
+SequentialExecutor
+Specint
+agentically
+denoises
+discoverable
+gentoo
+imatmul
+jenkins
+mopa
+perfetto
+translational
+tunable
+vlx

content/install-guides/gemini.md

@@ -1,8 +1,6 @@
 ---
 title: Gemini CLI
 
-draft: true
-
 author: Jason Andrews
 minutes_to_complete: 15
 official_docs: https://ai.google.dev/gemini-api/docs/cli
@@ -82,11 +80,11 @@ Benefits of using Vertex AI:
 
 ## How do I install Gemini CLI on macOS?
 
-The easiest way to install Gemini CLI on macOS is using Homebrew, which handles all dependencies automatically.
+The easiest way to install Gemini CLI on macOS is using Homebrew, which handles all dependencies.
 
 ### Install Gemini CLI on macOS using Homebrew
 
-Yes, you can install [Homebrew](https://brew.sh/) if it isn't already available on your computer.
+You can install [Homebrew](https://brew.sh/) if it isn't already available on your computer.
 
 Install Gemini CLI using Homebrew:
 
@@ -98,7 +96,7 @@ This installs Gemini CLI and automatically handles the Node.js dependency. The H
 
 ### Install Gemini CLI on macOS using npm
 
-Yes, if you prefer to use npm or need the latest version, you can install Gemini CLI globally using npm.
+If you prefer to use npm or need the latest version, you can install Gemini CLI globally using npm.
 
 First, make sure you have Node.js version 20 or higher installed. Install Node.js using Homebrew:
 
@@ -112,7 +110,7 @@ Verify Node.js is installed correctly:
 node --version
 ```
 
-The output should show version 20 or higher:
+The output is similar to:
 
 ```output
 v25.2.1
@@ -124,7 +122,7 @@ Install Gemini CLI globally using npm:
 npm install -g @google/gemini-cli
 ```
 
-This installs the latest version (for example, 0.20.0) directly from npm. Homebrew can lag behind npm, so versions may differ.
+This installs the latest version, such as 0.23.0, directly from npm. Homebrew can lag behind npm, so versions might differ.
 
 ### How do I confirm Gemini CLI is working on macOS?
 
@@ -136,10 +134,10 @@ Confirm the CLI is available by checking the version:
 gemini --version
 ```
 
-The output shows the version:
+The output is similar to:
 
 ```output
-0.20.0
+0.23.0
 ```
 
 Start an interactive session to test basic functionality:
@@ -164,7 +162,7 @@ Install the required packages on Ubuntu/Debian systems:
 sudo apt update && sudo apt install -y curl
 ```
 
-If you are not using Ubuntu/Debian use your package manager to install curl.
+If you're not using Ubuntu/Debian, use your package manager to install curl.
 
 ### How do I install Node.js on Arm Linux?
 
@@ -194,7 +192,7 @@ Verify npm is available:
 npm --version
 ```
 
-The output shows the npm version:
+The output is similar to:
 
 ```output
 10.2.4
@@ -225,7 +223,7 @@ gemini --version
 The output shows the version:
 
 ```output
-0.20.0
+0.23.0
 ```
 
 ### How do I view the available command-line options?
@@ -361,7 +359,7 @@ You may have other objects already in the file so make sure to use a `,` at the
         "run",
         "--rm",
         "-i",
-        "-v", "/Users/yourname01/yourlocalcodebase:/workspace",
+        "-v", "$HOME/workspace:/workspace",
         "--name", "arm-mcp",
         "armlimited/arm-mcp:latest"
       ],
@@ -382,14 +380,33 @@ Start the Gemini CLI and list the tools from the MCP server to verify it's worki
 gemini
 ```
 
-Use the `/tools` command to list the available tools:
+The output shows the MCP server.
+
+```output
+ Using: 1 GEMINI.md file | 1 MCP server
+```
+
+Use the `/mcp` command to list the available tools:
 
 ```console
-/tools
+/mcp
 ```
 
-You should see the Arm MCP server tools listed in the output. If the arm-mcp server says it's still loading, wait a moment and run `/tools` again.
+The Arm MCP server tools are listed in the output. 
+
+```output
+Configured MCP servers:
+
+🟢 arm_mcp_server - Ready (6 tools)
+  Tools:
+  - check_image
+  - knowledge_base_search
+  - mca
+  - migrate_ease_scan
+  - skopeo
+  - sysreport_instructions
+```
 
-If you're facing issues or have questions, reach out to mcpserver@arm.com .
+If you're facing issues or have questions, reach out to mcpserver@arm.com.
 
-You're ready to use the Gemini CLI.
+You're now ready to use Gemini CLI with the Arm MCP server for Arm-specific development assistance.

content/learning-paths/mobile-graphics-and-gaming/_index.md

@@ -9,15 +9,15 @@ key_ip:
 - Mali
 maintopic: true
 operatingsystems_filter:
-- Android: 33
-- Linux: 33
-- macOS: 14
+- Android: 35
+- Linux: 35
+- macOS: 15
 - Windows: 14
 subjects_filter:
 - Gaming: 6
 - Graphics: 6
-- ML: 16
-- Performance and Architecture: 35
+- ML: 17
+- Performance and Architecture: 36
 subtitle: Optimize Android apps and build faster games using cutting-edge Arm tech
 title: Mobile, Graphics, and Gaming
 tools_software_languages_filter:
@@ -35,20 +35,21 @@ tools_software_languages_filter:
 - Bazel: 1
 - C: 5
 - C#: 3
+- C++: 1
 - CCA: 1
 - Clang: 12
 - CMake: 2
-- CPP: 14
+- CPP: 15
 - Docker: 1
-- ExecuTorch: 3
+- ExecuTorch: 4
 - Frame Advisor: 1
 - GCC: 12
 - Generative AI: 2
 - Godot: 1
 - Google Pixel 8: 1
 - Google Test: 1
 - Halide: 1
-- Hugging Face: 5
+- Hugging Face: 6
 - Java: 6
 - Jupyter Notebook: 1
 - KleidiAI: 2
@@ -62,8 +63,9 @@ tools_software_languages_filter:
 - MTE: 2
 - NEON: 1
 - ONNX Runtime: 1
+- ONNX runtime: 1
 - OpenGL ES: 1
-- Python: 7
+- Python: 8
 - PyTorch: 2
 - QEMU: 1
 - RenderDoc: 1

content/learning-paths/mobile-graphics-and-gaming/build-llama3-chat-android-app-using-executorch-and-xnnpack/6-build-android-chat-app.md

@@ -17,6 +17,7 @@ In this section, you will use a Android demo application to demonstrate local in
     ``` bash
     export ANDROID_NDK=$ANDROID_HOME/ndk/29.0.14206865/
     export ANDROID_ABI=arm64-v8a
+    export ANDROID_SDK=$ANDROID_HOME
     ```
 
 {{% notice Note %}}

content/learning-paths/mobile-graphics-and-gaming/performance_onnxruntime_kleidiai_sme2/_index.md

@@ -0,0 +1,59 @@
+---
+title: Unleashing SME2 Performance - Profile ONNX models with KleidiAI-Optimized ONNX Runtime
+
+draft: true
+cascade:
+    draft: true
+
+minutes_to_complete: 40
+
+who_is_this_for: This is an advanced topic for software developers, performance engineers, and AI practitioners 
+
+learning_objectives: 
+    - Build ONNX runtime library with KleidiAI and SME2 support
+    - Profile performance of ONNX models
+    - Learn how KleidiAI and SME2 accelerates ONNX operators
+
+prerequisites:
+    - Knowledge of KleidiAI and SME2
+    - An Android device with Arm SME2 support
+
+author: Zenon Zhilong Xiu
+
+### Tags
+skilllevels: Advanced
+subjects: ML
+armips:
+    - Arm C1 CPU
+    - Arm SME2 unit
+tools_software_languages:
+    - C++
+    - ONNX runtime
+operatingsystems:
+    - Android
+    - Linux
+
+
+
+further_reading:
+    - resource:
+        title: part 1 Arm Scalable Matrix Extension Introduction 
+        link: https://developer.arm.com/community/arm-community-blogs/b/architectures-and-processors-blog/posts/arm-scalable-matrix-extension-introduction
+        type: blog
+    - resource:
+        title: part 2 Arm Scalable Matrix Extension Instructions 
+        link: https://developer.arm.com/community/arm-community-blogs/b/architectures-and-processors-blog/posts/arm-scalable-matrix-extension-introduction-p2
+        type: blog
+    - resource:
+        title: part4 Arm SME2 Introduction 
+        link: https://developer.arm.com/community/arm-community-blogs/b/architectures-and-processors-blog/posts/part4-arm-sme2-introduction
+        type: blog
+        
+
+
+### FIXED, DO NOT MODIFY
+# ================================================================================
+weight: 1                       # _index.md always has weight of 1 to order correctly
+layout: "learningpathall"       # All files under learning paths have this same wrapper
+learning_path_main_page: "yes"  # This should be surfaced when looking for related content. Only set for _index.md of learning path content.
+---

content/learning-paths/mobile-graphics-and-gaming/performance_onnxruntime_kleidiai_sme2/_next-steps.md

@@ -0,0 +1,8 @@
+---
+# ================================================================================
+#       FIXED, DO NOT MODIFY THIS FILE
+# ================================================================================
+weight: 21                  # The weight controls the order of the pages. _index.md always has weight 1.
+title: "Next Steps"         # Always the same, html page title.
+layout: "learningpathall"   # All files under learning paths have this same wrapper for Hugo processing.
+---

content/learning-paths/mobile-graphics-and-gaming/performance_onnxruntime_kleidiai_sme2/build_ort.md

@@ -0,0 +1,66 @@
+---
+title: Build ONNX Runtime with KleidiAI and SME2 for Android
+weight: 4
+
+### FIXED, DO NOT MODIFY
+layout: learningpathall
+---
+
+## Build ONNX Runtime and benchmark application with KleidiAI and SME2 support for Android
+
+To run this on an Android device, you must cross-compile ORT using the Android NDK.
+
+Prerequisites:
+-	Android NDK: Version r26b or newer (r27+ recommended for latest SME2 toolchain support).
+-	CMake & Ninja: Ensure these are in your system PATH.
+
+### Build `onnxruntime`
+
+First, clone the [ONNX Runtime](https://github.com/microsoft/onnxruntime).
+
+Then run the following from the root of the ONNX Runtime repository:
+```bash
+./build.sh --android --android_sdk_path $ANDROID_NDK_HOME --android_ndk_path $ANDROID_NDK_HOME --android_abi arm64-v8a --android_api 27 --config RelWithDebInfo --build_shared_lib --cmake_extra_defines onnxruntime_USE_KLEIDIAI=ON --cmake_generator Ninja --parallel
+```
+
+Note: The flag `onnxruntime_USE_KLEIDIAI=ON` triggers the inclusion of Arm KleidiAI kernels into the MLAS library.
+
+## Profiling Performance with onnxruntime_perf_test
+Once the build is complete, you will find the `libonnxruntime.so` shared library and `onnxruntime_perf_test` binary in your build directory.
+
+`onnxruntime_perf_test` is essential for measuring latency and identifying bottlenecks of an ONNX model (named `<your_model>.onnx` hereafter).
+
+### Step 1: Push files to Android Device
+```bash
+adb push <build_dir>/Android/RelWithDebInfo/onnxruntime_perf_test /data/local/tmp/
+adb push <build_dir>/Android/RelWithDebInfo/libonnxruntime.so  /data/local/tmp/
+adb push <your_model>.onnx /data/local/tmp/
+```
+
+### Step 2: Run the Performance Test
+The `onnxruntime_perf_test` tool allows you to simulate inference and gather statistics. For example,
+```bash
+# Execute on the device
+adb shell "/data/local/tmp/onnxruntime_perf_test -e cpu -m times  -r 20 -s -Z  -x 1 /data/local/tmp/<your_model>.onnx"
+```
+
+The command example set the arguments of the application as,
+-	`-e cpu` specifies the provider as cpu provider
+-	`-m times` specifies the test mode as “times”
+-	`-r 20` specifies the repeated times as 20
+-	`-Z` disallows thread from spinning during runs to reduce cpu usage
+-	`-s` shows statistics result
+-	`-x 1` sets the number of threads used to parallelize the execution within nodes as 1
+
+You can try other arguments setting if you would like to.
+
+### Step 3: Deep Dive into Operator Profiling
+To see exactly how many milliseconds are spent on each operator, use the profiling flag `-p`.
+```bash
+adb shell "/data/local/tmp/onnxruntime_perf_test -p profile.json -e cpu -m times  -r 5 -s -Z  -x 1 /data/local/tmp/<your_model>.onnx"
+adb pull /data/local/tmp/profile.json
+```
+
+The argument `-p` enables performance profiling during the benchmark run. When you provide this flag followed by a filename, ONNX Runtime will generate a JSON file containing a detailed trace of the model execution.
+You can view the results by opening [perfetto tool]( https://ui.perfetto.dev/), and loading the generated JSON file. This allows you to see a visual timeline of which operations took the most time.
+You also can convert the JSON file to a CSV sheet by creating a python script.