iWave Systems Ultra-High-Performance FPGA Platforms for AI/ML accelerated Edge Computing in IoT applications

October 23, 2019


iWave Systems Ultra-High-Performance FPGA Platforms for AI/ML accelerated Edge Computing in IoT applications

We have expended state of the art Xilinx Zynq? UltraScale+?MPSoC FPGA modules to bring forth intelligence in edge devices using advanced AI/ML accelerations.

With the advent of IoT and the proliferation of connected embedded devices, one of the biggest challenges in developing competitive IoT solutions is the ability to bring intelligence at the Edge of the IoT networks. Edge computing is crucial in IoT applications as it paves the way for faster real-time inference by embedding computation capability in on-premise infrastructure resulting in a dramatic improvement in overall system reliability and performance.

With edge computing increasingly forming the foundation of next-generation secure and connected devices, it is important to highlight the significance played by the hardware accelerators in determining system performance & efficiency and therefore should be considered with utmost importance while developing edge gateway solutions.

Over the years significant advancement in FPGA technology has led to FPGAS becoming mainstream for developing intelligent edge platforms.  FPGAs sophisticated performance and adaptability coupled with their ability to deliver the highest throughput at the lowest latency makes them ideal for enabling highly responsive real-time inference at the edge.

At iWave Systems, a leading FPGA design house based in Bangalore, we have expended state of the art Xilinx Zynq® UltraScale+™MPSoC FPGA modules to bring forth intelligence in edge devices using advanced AI/ML accelerations. iWave's Zynq® UltraScale+™MPSoC FPGA SOM offers versatile hardware accelerations for intuitive deployment of functions such as, image /speech recognition, object /pose detection, etc. and a flexible platform that enables developers to continually refine features and sharpen their competitive edge. Implementing artificial neural networks in FPGAs provides the flexibility to adapt applications with changing standards and end-user demands, which in turn future proofs your designs.

iWave also provides comprehensive Zynq® UltraScale+™MPSoC development platforms for an immediate evaluation of AI/ML applications.

Xilinx/DeePhi core platforms for AI/ML inference in iWave's Zynq® UltraScale+™MPSoC SOM

The Zynq UltraScale+ MPSoC SOM features an intelligent blend of MPSoC and FPGA functionality in an ARM® + Xilinx FPGA architecture that forms a highly integrated & powerful embedded platform for edge applications. The heterogeneous ARM® multicore processors complement the edge applications with high-performance non-real-time processing such as system boot, peripherals management, server communication, etc., while offloading the FPGA to execute critical real-time tasks using Deephi algorithms.

Deephi core platforms integrate both hardware and software components, presenting a comprehensive framework for AI/ML acceleration in applications such as face recognition, real-time surveillance, image / pose detection, etc. With its industry-leading AI/ML capabilities, the Xilinx/ Deephi core platform allows high-level adaptiveness to various workload characteristics and complement edge applications with ultra-low latency real-time inference.

With its support for a wide range of Neural Networks, the Xilinx/ Deephi core platforms are continuously evolving, integrating new and advanced algorithms for improved determinacy and inference in AI/ML applications. iWave supports a huge portfolio of Deephi cores enabling customers to choose from a variety of algorithms based on their application needs which allow for superior inference at edge applications. Refer the link https://www.xilinx.com/products/design-tools/ai-inference.html#models to gain insights about the various neural networks supported by Xilinx/ Deephi .

AI/ML acceleration for industrial edge application: (Few use cases)

  • Smart video surveillance system: Intelligent platforms that perform real-time monitoring and detection for smart inference at the device using a combination of FPGA acceleration and neural networks.                
  • Intuitive ADAS: Real-time computing platform capable of generating accurate and timely inferences with AI/ML algorithms on-board to assist drivers with information for appropriate decision making.
  • Industrial Automation: Adaptive intelligent devices that can sense, connect and compute massive data influx, perform predictive maintenance and generate smart intuitive decisions.
  • Smart health care: AI/ML accelerated devices that enable real-time monitoring and diagnosis of health for early detection of troubles or diseases and enables personalized treatment for patients.                       

Needless to say, edge computing continues to revolutionize the IoT ecosystem with competitive applications that enable the best consumer experience. iWave's Xilinx/Deephi platforms offers high-performance adaptive hardware acceleration for implementing AI/ML acceleration in edge applications with utmost flexibility and ease of use enabling developers to accelerate innovation and bring designs to life fast at optimized cost and lead time.

For further information or inquiries please write to [email protected] or contact our Regional Partners.