Arm NN

Software Developer Kit (SDK)

Arm NN is an inference engine for CPUs, GPUs and NPUs. It bridges the gap between existing NN frameworks and the underlying IP. It enables efficient translation of existing neural network frameworks, such as TensorFlow and Caffe, allowing them to run efficiently, without modification, across Arm Cortex-A CPUs, Arm Mali GPUs and Arm Ethos NPUs.

Arm NN is free of charge.

Download Arm NN SDK

About Arm NN SDK

Arm NN SDK is a set of open-source Linux software and tools that enables machine learning workloads on power-efficient devices. It provides a bridge between existing neural network frameworks and power-efficient Cortex-A CPUs, Arm Mali GPUs and Arm Ethos NPUs.

Arm NN SDK utilizes the Compute Library to target programmable cores, such as Cortex-A CPUs and Mali GPUs, as efficiently as possible. Arm NN does not provide support for Cortex-M CPUs.

The latest release supports Caffe, TensorFlow, TensorFlow Lite, and ONNX. Arm NN takes networks from these frameworks, translates them to the internal Arm NN format and then, through the Compute Library, deploys them efficiently on Cortex-A CPUs, and, if present, Mali GPUs such as the Mali-G71 and Mali-G72.

In September 2018, Arm donated Arm NN to the Linaro Machine Intelligence Initiative, where it is now developed fully in open source. To find out more, visit mlplatform.org.

 

 

Neural Network SDK Diagram.
Neural Network Diagram for Android.

Arm NN for Android

Also available is Arm NN for NNAPI, Google’s interface for accelerating neural networks on Android devices, made available in Android O. By default, NNAPI runs neural network workloads on the device’s CPU cores, but also provides a Hardware Abstraction Layer (HAL) that can target other processor types, such as GPUs. Arm NN for Android NNAPI provides this HAL for Mali GPUs. A further release adds support for Arm Ethos-N NPUs. 

Arm support for Android NNAPI gives >4x performance boost.

Learn more

Download Arm NN for Android sources. 

Download here

Arm NN performance relative to other NN frameworks

  • Arm NN open-source collaboration enables optimal third-party implementations
  • Deployed in multiple production devices (>250Mu)

Support for Cortex-M CPUs

Machine learning support for Cortex-M microcontrollers is provided by TensorFlow Lite Micro. Further optimization is available via CMSIS-NN, a collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Cortex-M processor cores.

Download CMSIS-NN

Arm NN future roadmap

Future releases of Arm NN will enable support for other machine learning frameworks as inputs, and other forms of processor cores as targets. This includes processor cores and accelerators from Arm’s partners, assuming availability of suitable extensions.

Information on the Machine Learning Platform.

Webinar - Project Trillium: Optimizing ML Performance for any Application

Project Trillium is a suite of Arm IP designed to deliver scalable ML and neural network functionality at any point on the performance curve, from sensors, to mobile, and beyond. 

 

Find out more

Community Forums

Not answered vldr d16, [r7, #200] ; 0xc8 causes Hard fault (Forced) 0 votes 71 views 0 replies Started 15 hours ago by Michael Anburaj Answer this
Not answered Where can I find the sc300 Technical reference manual? 0 votes 53 views 0 replies Started yesterday by YimoYimo Answer this
Suggested answer How to change CM33 State from secure to non-secure
  • TrustZone for Armv8-M
  • Cortex-M33
0 votes 163 views 1 replies Latest yesterday by 42Bastian Schick Answer this
Not answered Transmitting and reconstructing DSP data over internet. 0 votes 143 views 0 replies Started 2 days ago by Phalelashvili Answer this
Answered Memory related issue with MCU startup ( __libc_init_array )
  • Toolchain
  • Cortex-M
  • stm32l4
0 votes 6286 views 8 replies Latest 3 days ago by Jacob Beningo Answer this
Suggested answer STM32H7 CAN FD issues
  • Cortex-M7
  • stm32 h7
  • Keil
0 votes 191 views 1 replies Latest 4 days ago by 42Bastian Schick Answer this
Not answered vldr d16, [r7, #200] ; 0xc8 causes Hard fault (Forced) Started 15 hours ago by Michael Anburaj 0 replies 71 views
Not answered Where can I find the sc300 Technical reference manual? Started yesterday by YimoYimo 0 replies 53 views
Suggested answer How to change CM33 State from secure to non-secure Latest yesterday by 42Bastian Schick 1 replies 163 views
Not answered Transmitting and reconstructing DSP data over internet. Started 2 days ago by Phalelashvili 0 replies 143 views
Answered Memory related issue with MCU startup ( __libc_init_array ) Latest 3 days ago by Jacob Beningo 8 replies 6286 views
Suggested answer STM32H7 CAN FD issues Latest 4 days ago by 42Bastian Schick 1 replies 191 views