Edge AI
Lowest latency, power and cost for multi-sensor analytics and machine learning applications at the Industrial IoT edge
Analytics and Machine Learning encompass a tremendous field of industrial applications, for instance Predictive Maintenance, Digital Twin model based control, anomaly detection and many other use cases. Xilinx and the Xilinx ecosystem offer multiple approaches to address these Edge applications based on user preferences.
Analytics and Machine Learning
Edge AI Platform
The Xilinx Edge AI Platform offers unique and patented Deep Learning Acceleration techniques for AI inference. It includes tools for compression (pruning & quantization) as well as compilation of Deep Neural Network 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 and TensorFlow.
PYNQ - Python on Zynq
PYNQ provides Python powered control, edge analytics and machine learning. 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 including Numpy, Scikit-Learn, and Pandas.
Cloud Provider
The trend in Industrial is a partial shift of processing from the Cloud to the Edge driven by:
- Physical assets demand low latency decisions/actions closest to the data acquisition point (typically under 10 ms)
- Data generated is typically large in size and moving and storing all generated data is not desirable due to OPEX cost, time and privacy concerns
Xilinx provides the industry’s most capable single-chip Edge embedded processing platforms to address such trends. Furthermore, Xilinx’s SoC portfolio and ecosystem partnerships with leading cloud service providers enable distribution of tasks across the Cloud and Edge as well as mobilize applications from the Cloud to Edge.
AWS IoT
Xilinx with AWS IoT provides differentiated and collaborative machine learning capabilities across Edge and Cloud
AWS IoT Greengrass: Seamlessly extends AWS to edge devices so they can act locally on the data they generate, while still using the cloud for management, analytics, and durable storage
AWS FreeRTOS: Operating system for microcontrollers that makes small, low-power edge devices easy to program, deploy, secure, connect, and manage
*AWS Sagemaker: Fully-managed service that covers the entire machine learning workflow to label and prepare your data, choose an algorithm, train the algorithm, tune and optimize it for deployment, make predictions, and take action
*AWS Robomaker: AWS RoboMaker is a service that makes it easy to develop, test, and deploy intelligent robotics applications at scale
Microsoft Azure IoT
Xilinx with Azure IoT provides differentiated and collaborative machine learning capabilities across Edge and Cloud
*Azure Sphere: Securely connect Zynq-powered devices across Edge and Cloud
*Azure IoT Hub: Connect, monitor and manage entire fleet of assets
*Azure IoT Edge: Extend cloud intelligence and analytics to Edge devices
*Azure IoT Digital Twins: Build next-generation spatial intelligence solutions
*under development, contact local FAE for latest updates
SoC Integration
Xilinx SDK
- Software Development Kit is the Integrated Design Environment for creating embedded applications on any of Xilinx's ARM-based SoCs or soft IP-based microprocessors
- SDK is the first application IDE to deliver true homogenous and heterogeneous multi-processor design, debug, and performance analysis
Vivado HLS
- Accelerates IP creation by enabling C, C++ and System C specifications to be directly targeted into Xilinx programmable devices without the need to manually create RTL
- Faster verification using C/C++ test bench simulation, automatic VHDL or Verilog simulation and test bench generation
SDSoC
- Software Defined System-on-Chip is a development environment tailored to tightly coupled hardware/software designs
- Allows seamless integration of hardware and software
- Automates and streamlines memory allocation, cache management, DMA, and device interaction
Solutions
| Solution Provider | Description | Device Support |
|---|---|---|
| Xilinx | Why Xilinx AI? | |
| Xilinx - Edge AI Platform | Edge AI Developer Hub DNNDK Edge White Paper |
Zynq UltraScale+ Zynq 7000 |
| Xilinx - PYNQ | PYNQ Homepage PYNQ Community Projects |
Zynq UltraScale+ Zynq 7000 |
| AWS IoT | AWS Certified Xilinx Products AWS IoT Xilinx – AWS Workshop |
Zynq UltraScale+ Zynq 7000 |
| Azure IoT | Azure IoT | Zynq UltraScale+ Zynq 7000 |
| Xilinx Tools | SDSoC Vivado HLx SDK |
Zynq UltraScale+ Zynq 7000 |
| Xilinx | SPYN Design Files Community Portal |
Zynq UltraScale+ Zynq 7000 |
Ecosystem Solutions
| Solution Provider | Description | Device Support |
|---|---|---|
| Kortiq | AIScale – Small and Efficient CNN Accelerator | Zynq UltraScale+ Zynq 7000 |
| Silicon Software | Visual Applets | Zynq UltraScale+ Zynq 7000 Kintex 7000 |
Some Industrial IoT products need all elements of the Xilinx IIoT Solutions Stack, all need some. The Xilinx IIoT Solutions Stack is comprised of optimized Xilinx and Ecosystem building blocks and solutions used across Industrial and Healthcare 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 Solutions stack.
