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 CPUs and Arm Mali GPUs.
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 Arm Cortex CPUs, Arm Mali GPUs or the Arm Machine Learning processor.
Arm NN SDK utilizes the Compute Library to target programmable cores, such as Cortex-A CPUs and Mali GPUs, as efficiently as possible. It includes support for the Arm Machine Learning processor. Arm NN does not yet 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.
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.
Support for Cortex-M CPUs
Arm NN is currently not compatible with Cortex-M microcontrollers. CMSIS-NN is 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.
|Not answered||MPU and TrustZone||0 votes||14 views||0 replies||Started 7 hours ago by Talk2Joseph||Answer this|
|Suggested answer||Cortex A15 SCU||0 votes||265 views||1 replies||Latest 8 hours ago by Christopher Tory||Answer this|
|Suggested answer||WT it non cache able memory when it broadcast at transaction||0 votes||162 views||1 replies||Latest 8 hours ago by Christopher Tory||Answer this|
|Not answered||Understanding XDMAC on Cortex-M7||0 votes||14 views||0 replies||Started 8 hours ago by Paul Braman||Answer this|
|Not answered||How can I debug two A53 cores in DS-5 tool||0 votes||18 views||0 replies||Started 17 hours ago by DriverLike||Answer this|
|Suggested answer||reference source code to verify the Cortex-R52||0 votes||89 views||1 replies||Latest 18 hours ago by Jorney||Answer this|
|Not answered||MPU and TrustZone Started 7 hours ago by Talk2Joseph||0 replies 14 views|
|Suggested answer||Cortex A15 SCU Latest 8 hours ago by Christopher Tory||1 replies 265 views|
|Suggested answer||WT it non cache able memory when it broadcast at transaction Latest 8 hours ago by Christopher Tory||1 replies 162 views|
|Not answered||Understanding XDMAC on Cortex-M7 Started 8 hours ago by Paul Braman||0 replies 14 views|
|Not answered||How can I debug two A53 cores in DS-5 tool Started 17 hours ago by DriverLike||0 replies 18 views|
|Suggested answer||reference source code to verify the Cortex-R52 Latest 18 hours ago by Jorney||1 replies 89 views|