mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-15 18:23:41 +00:00
3681048474
### Description Staged: https://faxu.github.io/onnxruntime/docs/performance/ Main changes: - Restructure performance section to break into sub-categories - Move CUDA specific perf tuning tips to [CUDA EP page](https://faxu.github.io/onnxruntime/docs/execution-providers/CUDA-ExecutionProvider.html#performance-tuning) - Update [Transformer optimizer page](https://faxu.github.io/onnxruntime/docs/performance/transformers-optimization.html) to remove version-specific content... will be supported along with https://github.com/microsoft/onnxruntime/pull/14964 - Fix links to point to new pages
36 lines
1.2 KiB
Markdown
36 lines
1.2 KiB
Markdown
---
|
|
title: Arm - Arm NN
|
|
description: Instructions to execute ONNX Runtime with Arm NN on Armv8 cores
|
|
grand_parent: Execution Providers
|
|
parent: Community-maintained
|
|
nav_order: 2
|
|
redirect_from: /docs/reference/execution-providers/ArmNN-ExecutionProvider
|
|
---
|
|
|
|
# ArmNN Execution Provider
|
|
{: .no_toc}
|
|
|
|
## Contents
|
|
{: .no_toc }
|
|
|
|
* TOC placeholder
|
|
{:toc}
|
|
|
|
Accelerate performance of ONNX model workloads across Armv8 cores with the ArmNN execution provider. [ArmNN](https://github.com/ARM-software/armnn) is an open source inference engine maintained by Arm and Linaro companies.
|
|
|
|
## Build
|
|
For build instructions, please see the [BUILD page](../../build/eps.md#armnn).
|
|
|
|
## Usage
|
|
### C/C++
|
|
To use ArmNN as execution provider for inferencing, please register it as below.
|
|
```
|
|
Ort::Env env = Ort::Env{ORT_LOGGING_LEVEL_ERROR, "Default"};
|
|
Ort::SessionOptions so;
|
|
bool enable_cpu_mem_arena = true;
|
|
Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_ArmNN(so, enable_cpu_mem_arena));
|
|
```
|
|
The C API details are [here](../../get-started/with-c.md).
|
|
|
|
## Performance Tuning
|
|
When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/main/onnxruntime/test/perftest), use the flag -e armnn
|