UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

Analytics & Machine Learning

Lowest latency, power and cost for multi-sensor analytics and machine learning applications at the Industrial IoT edge

Analytics and machine learning has tremendous application in Industrial from predictive maintenance, digital twin model based control, anomaly detection and many other use cases.  Xilinx and the Xilinx ecosystem offer multiple different approaches to address these edge applications based on user trends.

Diagram

One approach is python powered control, edge analytics and machine learning enabled by PYNQ. PYNQ is a software-hardware framework for Zynq SoCs leveraging the programmable hardware to pre-process sensor and other types of data to make software analysis and manipulation highly efficient in an embedded processor.  PYNQ supports all major python libraries like Numpy, Scikit-Learn, and Pandas etc.

The second approach is to use software callable machine learning IPs powered by DEEPHi. DEEPHi offers unique and patented Deep Learning Acceleration techniques for inference. Included are tools for compression (pruning & quantization) as well as compilation of DNN models. Pre-pruned reference models for popular networks are readily available for fast implementation. Networks are primarily focused on classification, segmentation, and detection. Supported deep learning frameworks are Caffe, TensorFlow and mxnet. SDSoC with DEEPHi integrated available 2018.2 or above.

Additionally, there are a growing number of ecosystem partners that support Industrial applications via the use of machine learning.

Industrial IoT is also rapidly accelerating the opportunity for cloud connected and collaborative control systems that can unlock the next set of capabilities of the industrial asset using machine learning. Industrial control system providers are realizing this vision and the need for integrated edge to cloud solutions that will accelerate their time to market. Xilinx integration with AWS IoT (AWS Greengrass and FreeRTOS) and Microsoft Azure (Edge and Sphere) provide differentiated and collaborative edge-to-cloud machine learning capabilities.

Solution Provider Description Device Support
Xilinx

PYNQ Homepage

PYNQ Community Projects

Zynq UltraScale+

Zynq 7000

Xilinx SPYN Design Files Zynq 7000
Xilinx (DEEPHi)

https://arxiv.org/pdf/1612.00694.pdf

http://www.deephi.com/technology.html

Zynq UltraScale+

Zynq 7000

Kortiq AIScale – Small and Efficient CNN Accelerator

Zynq UltraScale+

Zynq 7000

Xilinx reVISION CHaiDNN Design Files Zynq UltraScale+  
Amazon Web Services AWS UltraScale and UltraScale+
Silicon Software Visual Applets

Zynq UltraScale+

Zynq 7000

Artix-7

Kintex-7

Kintex UltraScale+

iiot-solutions-stack

Some Industrial IoT products need all elements of the Xilinx IIoT Solution Stack, all need some. The Xilinx IIoT Solution Stack is comprised of optimized Xilinx and Ecosystem building blocks and solutions used across Industrial IoT platforms. Starting from scratch is never something you will have to do with a Xilinx-based Industrial IoT system. Minimize development time and cost and maximize design reuse on your next Industrial IoT platform by exploring the different elements of the Xilinx IIoT Solution stack.

Page Bookmarked