ArmNN Execution Provider

ArmNN is an open source inference engine maintained by Arm and Linaro companies. The integration of ArmNN as an execution provider (EP) into ONNX Runtime accelerates performance of ONNX model workloads across Armv8 cores.

Build ArmNN execution provider

For build instructions, please see the BUILD page.

Using the ArmNN execution provider

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 sf;
bool enable_cpu_mem_arena = true;
Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_ArmNN(sf, enable_cpu_mem_arena));

The C API details are here.

Performance Tuning

For performance tuning, please see guidance on this page: ONNX Runtime Perf Tuning

When/if using onnxruntime_perf_test, use the flag -e armnn