MediaTek Backend on ExecuTorch

MediaTek backend empowers ExecuTorch to speed up PyTorch models on edge devices that equips with MediaTek Neuron Processing Unit (NPU). This document offers a step-by-step guide to set up the build environment for the MediaTek ExecuTorch libraries.

Supported Chips

The examples provided in this repository are tested and supported on the following MediaTek chip:

MediaTek Dimensity 9300 (D9300)

Build Instructions

Prerequisites

Before you begin, ensure you have the following prerequisites installed and configured:

1. Buck2 Build Tool

Download Buck2: Obtain Buck2 from the official releases page.
Add to PATH: Extract the downloaded file and add the directory to your system's $PATH environment variable.
```
export PATH=<path_to_buck>:$PATH
```

2. Android NDK

Download Android NDK: Acquire the Android NDK version 26.3.11579264 from the Android developer site.
Set NDK Path: Ensure that the $ANDROID_NDK environment variable is set to the path where the NDK is located.
```
export ANDROID_NDK=<path_to_android_ndk>
```

3. MediaTek ExecuTorch Libraries

Download NeuroPilot Express SDK from MediaTek's NeuroPilot portal:

libneuronusdk_adapter.mtk.so: This universal SDK contains the implementation required for executing target-dependent code on the MediaTek chip.
libneuron_buffer_allocator.so: This utility library is designed for allocating DMA buffers necessary for model inference.
mtk_converter-8.8.0.dev20240723+public.d1467db9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl: This library preprocess the model into a MediaTek representation.
mtk_neuron-8.2.2-py3-none-linux_x86_64.whl: This library converts the model to binaries.

Setup

Follow the steps below to setup your build environment:

Setup ExecuTorch Environment: Refer to the Setting up ExecuTorch guide for detailed instructions on setting up the ExecuTorch environment.
Setup MediaTek Backend Environment

Install the dependent libs. Ensure that you are inside backends/mediatek/ directory
```
pip3 install -r requirements.txt
```

Install the two .whl downloaded from NeuroPilot Portal

pip3 install mtk_neuron-8.2.2-py3-none-linux_x86_64.whl
pip3 install mtk_converter-8.8.0.dev20240723+public.d1467db9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Set evironment variables for building backend

export NEURON_BUFFER_ALLOCATOR_LIB=<path_to_buffer_allocator>

Build

Navigate to scripts/ directory.
Build MediaTek Backend: Once the prerequisites are in place, run the mtk_build.sh script to start the build process, MediaTek backend will be built under cmake-android-out/backends/ as libneuron_backend.so
```
./mtk_build.sh
```

Run

Push MediaTek universal SDK and MediaTek backend to the device: push libneuronusdk_adapter.mtk.so and libneuron_backend.so to the phone and export it to the $LD_LIBRARY_PATH environment variable before executing ExecuTorch with MediaTek backend.
```
export LD_LIBRARY_PATH=<path_to_usdk>:<path_to_neuron_backend>:$LD_LIBRARY_PATH
```

Please refer to executorch/examples/mediatek/ for export and execution examples of various of models.