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 the Arm Machine Learning processor.
Arm NN is free of charge.
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 the Machine Learning processor.
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.
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 the Arm Machine Learning processor.
Arm support for Android NNAPI gives >4x performance boost.
Download Arm NN for Android sources.
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.
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.
|Suggested answer||Can i change SP at run time in CM33?||0 votes||30 views||1 replies||Latest 5 hours ago by Joseph Yiu||Answer this|
|Suggested answer||Monitor Mode Debug||0 votes||511 views||6 replies||Latest 5 hours ago by Andy Neil||Answer this|
|Not answered||Audio mixing efficiently and hard realtime requirment||0 votes||52 views||0 replies||Started 16 hours ago by Manojkumar Subramaniam||Answer this|
|Not answered||Are there any Cortex-M controller with h.264 encoder?||0 votes||59 views||0 replies||Started yesterday by Vick||Answer this|
|Answered||32-bit encoding hex values for Arm instructions||0 votes||263 views||3 replies||Latest yesterday by BQL||Answer this|
|Suggested answer||Memory Protection Unit - Complexity in usage||0 votes||434 views||5 replies||Latest 2 days ago by 42Bastian Schick||Answer this|
|Suggested answer||Can i change SP at run time in CM33? Latest 5 hours ago by Joseph Yiu||1 replies 30 views|
|Suggested answer||Monitor Mode Debug Latest 5 hours ago by Andy Neil||6 replies 511 views|
|Not answered||Audio mixing efficiently and hard realtime requirment Started 16 hours ago by Manojkumar Subramaniam||0 replies 52 views|
|Not answered||Are there any Cortex-M controller with h.264 encoder? Started yesterday by Vick||0 replies 59 views|
|Answered||32-bit encoding hex values for Arm instructions Latest yesterday by BQL||3 replies 263 views|
|Suggested answer||Memory Protection Unit - Complexity in usage Latest 2 days ago by 42Bastian Schick||5 replies 434 views|